cs.AI · 2026-08-05 · No. 75
Artificial Intelligence, 2026-08-05.
75 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
75 entries-
01
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin, Aniri, Shuo Lu, Wenke Huang, Hu Cao, Xun Xiao, Zhihong Zhu, Volker Tresp, Fei...
cs.AI
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories from stronger expert models. However, when the expert fails on harder problems, existing trajectory-guided methods lose their main source of supervision, and these failed trajectories are typically discarded as negative samples. We argue that such failures, which we...
-
02
Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations
Zizhao Hu, Nathan Elijah Segura, Mohammad Rostami, Jesse Thomason
cs.AI
Human input reaches language models by typing or speaking, and each channel leaves a distinct signature: orthographic noise for keyboards; for voice, disfluency from conventional transcription and restructuring from AI-backed dictation tools. How do they impact an LLM's performance? In this paper we present HIVE (Human Input-Variation Engine), a suite of voice transcription perturbations and QWERTY keyboard perturbations. We use HIVE to...
-
03
Interpretable Adaptive Sampling for LLM Test-Time Scaling
Mobina Kashaniyan, Ali Jannesari
cs.AI
Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that spend the same compute on easy and difficult prompts. These fixed budgets are also difficult to inspect because they do not explain why a given prompt receives a particular number of samples. We propose adaptive} test-time scaling with a lightweight fuzzy controller that maps interpretable...
-
04
A game theory for foundation models shows new paths to rational cooperation through similarity inference
Alexander Meulemans, Maciej Wołczyk, Marissa A. Weis, Rajai Nasser, Roberta Rocca, Seijin Kobayashi, Guillaume...
cs.AI
As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing their collective behavior is essential for ensuring safety and cooperation. Classical game theory, the dominant framework for modeling rational interaction, is built upon the assumption of `decoupled agency,' where agents treat their own decision-making as independent of the environment and...
-
05
TACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring
Dongjie Yang, Siyan Lin, Leixian Shen, Rui Sheng, Huamin Qu, Zixin Chen
cs.AI
Large language models (LLMs) are increasingly used to provide conversational practice for English-as-a-second-language (ESL) learners. Effective ESL tutoring, however, requires more than fluent response generation: a tutor must select an appropriate pedagogical action based on learner behavior and dialogue context. Human-tutoring research offers principles for adaptive support, but they are often task-specific and remain insufficiently...
-
06
The Transformer Revolution, Part 1: Dynamic Processing through Output- Weight Interconnections
Marco Giunti, Fabrizia Giulia Garavaglia
cs.AI · cs.NE
This paper offers a new interpretation of the Transformer during inference. Against the "stochastic parrot" view that large language models merely reproduce statistical regularities learned in training, we argue that Transformers construct and apply prompt-dependent transformations whose parameters are generated during inference. We call this form of computation SIDPP: Sequence-level Interactive Dynamic Parallel Processing. The Transformer is...
-
07
Implementing Causal Perception: Competing SCMs and Situated Fairness
Jose M. Álvarez
cs.AI
Causal perception occurs when agents with competing Structural Causal Models (SCMs) of the same system infer different probability distributions, including the hypothetical distributions implied by each agent's SCM under the same set of interventions. It shapes how agents reason about the system and how they perceive its fairness. Causal perception is a promising probabilistic framework, but it has remained purely theoretical. This work...
-
08
Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory
Matt Ratto, Abhishek Moturu, Daniel Silver
cs.AI · cs.LG · cs.MA
As AI systems are deployed across increasingly diverse social contexts, alignment can no longer be framed as the optimization of a single, unified set of values. Instead, systems must be able to recognize, represent, and respond to multiple legitimate perspectives. This has led to growing interest in pluralistic alignment, which seeks to move beyond one-size-fits-all models of appropriate behaviour. However, current approaches often lack a...
-
09
When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking
Shaofeng Liang, Runwei Guan, Wenshuo Chen, Jiemin Wu, Bowen Tian, Haozhe Jia, Kaishen Yuan, Songning Lai, Daizong...
cs.AI
Resource constraints on UAV platforms have driven a paradigm shift in aerial tracking, from pursuing performance toward balancing accuracy with efficiency. Adaptive Transformer Trackers, which leverage an input-dependent dynamic routing architecture, have emerged as a representative solution to this challenge. However, we reveal that behind this computation-on-demand flexibility hides a critical structural flaw: the Lipschitz singularity of...
-
10
Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition
Michal Mráz, Justin Shenk
cs.AI
We study linear representations of temporal horizon in the large language model Qwen3-32B and use them to change the model's time-related preferences, recommendations, and capabilities. We train contrastive linear probes on teacher-forced temporal-choice answers to find a short-term versus long-term direction in the model's residual stream, and evaluate contrastive activation-addition steering on a held-out binary temporal-choice task, an...
-
11
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
Tianyi Guan, Yiding Wang, Haotong Yang, Siyuan Cao, Shirui Liu, Yi Hu, Jiaqi Li, Muhan Zhang
cs.AI · cs.CL · cs.LG
Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectively evolve their skills and whether the resulting skills improve task-solving capabilities. To bridge this gap, we introduce ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning. It covers five representative domains, each containing 100...
-
12
ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories
Yash Misra, Javal Vyas, Siddharth Gutta, Mehmet Mercangöz
cs.AI · eess.SY
This white paper presents ADMITBench, a reference framework for evaluating industrial LLM advisories at the level of the proposed action. The framework implements a versioned, safety-governed evaluation contract that checks whether a recommendation is supported by the available evidence, permitted under the stated authority and procedure, and acceptable under the plant-specific consequence checks encoded in the selected evaluation profile. In...
-
13
MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM Agents
Jiaming Chen, Yisen Gao, Yanping Li, Zifan Liu, Yumeng Zhang, Jun Zhang
cs.AI
Memory-augmented LLM agents rely on rich context for long-horizon reasoning and acting, yet their memory modules expose a persistent attack surface for malicious records, making the study of memory poisoning threats imperative. However, existing query-only attacks often fail to remain effective in two realistic and prevalent settings: large-scale benign memory pools and active input auditing. Consequently, current approaches fall short when...
-
14
Oilbird: Training-Free Speculative Decoding with Keys the Verifier Already Computes
Tao Jin, Phuong Minh Nguyen, Zhenzhu Yan, Teeradaj Racharak, Naoya Inoue
cs.AI
Training-free speculative decoding drafts by matching an exact suffix of the context against a pool of earlier context. That lookup misses correct drafts already in the pool, most visibly on tool-calling traffic, where a request repeats almost everything but the few values minted for it, and where one rejected token discards the correct continuation behind it. We diagnose the failure position by position across ten benchmarks and find it to...
-
15
LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards
Zhinan Liu, Jie Li, Mingyu Kang, Jiayi Ji
cs.AI
Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent-reasoning methods reduce token generation by moving reasoning into continuous states, they remain underexplored for safety moderation and lack an inspection interface for deployment. In this paper, we propose LatentGuard, an efficient and inspectable safeguard framework that brings continuous...
-
16
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
Chunlin Liu, Junnian Chen, Haitong Jiang, Jianyu Zhao, Yingsen Pang, Jingchen Li, Jiabiao He, Youming Lu, Jinhe Bi, Yuntao Du
cs.AI
Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora. Removing such knowledge is essential for building trustworthy AI systems. However, existing studies primarily focus on forgetting within individual modalities. Although recent work has begun to explore cross-modal consistency in unlearning, the cross-modal transfer of real-world knowledge...
-
17
KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation
Ruihan Li, Jiyang Tan, Kailin Jiang, Huining Li, Hengyang Lu, Yu Huang, Qian Li, Yuntao Du
cs.AI
Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs). While existing benchmarks mainly focus on entity, attribute, and relation hallucinations, knowledge-related failures are often investigated separately, lacking a unified evaluation framework across different hallucination dimensions. To overcome this, we propose \textbf{KnowHal}, a benchmark that explicitly incorporates knowledge...
-
18
Computing Actual Causes for Neural Network Predictions under Structured Causal Inputs
Jannick Strobel, Muqsit Azeem, Stefan Leue
cs.AI · cs.LG · cs.LO
Explaining the predictions of neural networks is a central challenge in trustworthy AI. Existing explanation methods, such as those based on feature attribution or minimal sufficient sets, typically treat input features as independent, which can yield misleading explanations when inputs exhibit structured dependencies. We address this by formalizing explanations as Halpern-Pearl (HP) actual causes, modeling input dependencies using Boolean...
-
19
GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
Leijun Zhou, Zhihao Liu, Xiang Qu, Chenxu Liu, Yifei Liu, Yanke Yu, Jingzhe Xu, Xuejun Wu, Buyue Qian, Xi Chen,...
cs.AI
Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively. Evaluating self-evolution is difficult: existing benchmarks provide limited coverage of economically valuable task domains, do not always design training and test tasks such that test-time gains can be attributed to training experience, and remain vulnerable to data contamination. We present GDPevo, an...
-
20
Risky Business: Measuring The Faithfulness-Safety Tension
Dominik Meier, Luca Joshua Francis, Marco Bernhard Kaiser, Terry Ruas, Jan Philip Wahle, Bela Gipp
cs.AI · cs.CL
Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring. However, monitoring relies on faithfulness, i.e., the model output strictly derives from its reasoning trace. We identify an alignment tension where a model must be faithful enough to be monitored, yet robust enough to reject unsafe reasoning. We demonstrate that this counterbalance exists in current Large Reasoning Models (LRMs), and show ways in which it can...
-
21
Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems
Sebastián Andrés Cajas Ordóñez, Agastya Munnangi, Aldo Marzullo, Felipe Ocampo Osorio, Quang Bui, Mohammad Shahin,...
cs.AI
Clinical decision support is moving toward committees of language-model agents deliberating on a shared workspace. We ask whether such committees can be gamed by shortcuts, cues a benchmark rewards but a clinician would ignore. Across seven cohorts on six public datasets spanning text (MedQA-USMLE, MedMCQA, MIMIC-CXR reports), imaging (NIH ChestX-ray14, MIMIC-CXR-JPG, CheXpert) and tabular ICU records (SUPPORT2), Gemini committees resist...
-
22
MissClick: Exploiting Digit-Serialized Coordinates to Attack GUI Grounding Models
Yu Ran, Wentao Zhao, Xin Zhang, Yi Pan
cs.AI
Recent GUI visual grounding models generate screen coordinates as sequences of digit tokens that are parsed into numerical values and mapped to executable clicks. The security implications of this coordinate generation process have been largely overlooked. We observe that each coordinate digit is predicted as a categorical token, yet after parsing, changing a hundreds-place digit by one changes the corresponding numerical coordinate component...
-
23
AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits
Shuo Ren, Yaohui Han, Libo Shen, Zhiqiang Jia, Rongliang Fu, Bei Yu, Tsung-Yi Ho
cs.AI
As Moore's law slows, the industry is turning to three-dimensional integration; yet in merged 3D-IC flows, routed designs expose bond-level defects with no 2D analogue, and post-route engineering change orders (ECO) remain manual, expertise-bound work. Worse, the standard edit-then-fully-reroute practice entangles a repair with router churn, so a signoff number cannot be attributed to the edit that motivated it. We present AgenticECO, an...
-
24
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
Chunyang Jiang, Pingping Zhang, Yuzhi Zhao, Wenao Ma, Zhijian Hou, Mengyang Wu, Yiyang Cai, Senkang Hu, Sitong...
cs.AI
Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision. However, existing MLLM self-augmentation methods are largely text-centric, while image...
-
25
CARE-Bench: Benchmarking Patient-Facing LLM Triage
Yining Hua, Hongbin Na, Cyrus Ayubcha
cs.AI
Patient-facing medical LLMs and agents increasingly answer symptom questions before clinician contact, where the key safety question is what action the user should take next. We introduce CARE-Bench, a source-grounded benchmark that evaluates sequential patient-facing triage as a four-label per-turn current-action task. CARE-Bench contains 500 cases and 1,059 evaluated patient-disclosure prefixes reconstructed from medical dialogue,...
-
26
SAT-Edge-Agent: Hardware-in-the-Loop Edge-Agent Orchestration for Onboard Satellite Intelligence
Longji He, Jeto Xu
cs.AI
Onboard satellite intelligence requires a task layer that translates mission intent into local tool calls, exposes execution state, and returns machine-consumable artifacts under communication and power constraints. We present SAT-Edge-Agent, a hardware-in-the-loop (HIL) edge-agent system deployed on a commercial off-the-shelf ARM-based heterogeneous edge system-on-chip. A browser workspace and FastAPI agent coordinate a local...
-
27
When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Coupling Diagnostic for Machine Collectives
Molood Arman
cs.AI · cs.CL
Collective intelligence research treats disagreement as evidence of epistemic diversity: if agents express different views, the group should retain capacity to revise. In LLM collectives this proxy can break: agents can produce diverse-looking arguments while preserving the same conclusion. We operationalize dispersion-revision coupling: the degree to which an intervention that verifiably increases the dispersion of a collective's outputs in...
-
28
Less Traffic, Better Outcomes: Competition-Aware Request Dispatch in Real-Time Ad Exchanges
Jonaid Shianifar, Blaz Mramor, Fangda Zou, Matthieu C. Martin, Xingsheng Guo, Zhihua Zhu, Rong Zhou, Bichen Shi
cs.AI · cs.LG
Real-time bidding (RTB) ad exchanges typically forward nearly all incoming requests to demand-side platforms (DSPs), even though only a small fraction receive bids. This over-distribution weakens auction outcomes: DSPs throttle participation under compute and budget constraints, reducing the effective use of limited bidding capacity. We present a competition-aware request dispatch framework that uses distributional bid prediction and...
-
29
TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents
Han Xiao, Hongjun Xu, Xin Zhang, Yidong Chen, Xiaodong Shi
cs.AI
Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems reduce memory updating to a binary Write/Hold decision, which cannot distinguish whether new information should be added, ignored, used to revise an outdated belief, rejected as unreliable, or deferred for verification. These choices may share the same binary label while producing...
-
30
LiveEvalBench: Toward Open-World Evaluation for Web Generation
Yiyao Wang, Zhen Wen, Yinghao Tang, Yixiao Fu, Lin Yuan, Xiaolau Zhang, Jun Zhou, Wei Chen
cs.AI · cs.SE
Large language models are increasingly capable of synthesizing executable frontend projects, yet existing benchmarks still treat web generation as a static evaluation problem. We argue that frontend artifacts demand a different paradigm: they are interactive rather than static, admit diverse yet equally valid implementations, and evolve faster than rigid pipelines can accommodate. To address these gaps, we present LiveEvalBench, an automated...
-
31
PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud
Chenghua Wang, Daliang Xu, Dongqi Cai, Duojin Sun, Hao Zhang, Haoze Qian, Huaiyuan Zhang, Jinshuo Cui, Kezhao Zhao,...
cs.AI · cs.RO
Physical AI policies require inference throughout their lifecycle, including model evaluation, cloud reinforcement learning rollout, edge GPU serving, and onboard deployment. Although these settings share the same checkpoint and action semantics, they often rely on separate inference programs. To unify them, we build PhyAI, a Physical AI inference engine with a single runtime that keeps architecture-specific conditioning, solver, cache, and...
-
32
Shielding for Higher-Order Safety
Filip Cano, Thomas A. Henzinger, Konstantin Kueffner
cs.AI
Safety shields are runtime enforcement mechanisms that restrict the actions of a controller to guarantee safety. Classical shields are usually synthesised for state predicates: the current physical state is either safe or unsafe, and the shield disables precisely those actions that can force the system into an unsafe state in the future. In many cyber-physical applications this view is too coarse. A vehicle approaching an obstacle should not...
-
33
Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training
Yibei Liu, Jiajun Chen, Qianle Zhang, Tangyue Jin, Mengying Zhu, Meng Xi, Yangyang Wu
cs.AI
Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models. Under pronounced task distributional shifts, however, forgetting across representative RFT algorithms escalates sharply. This stems from the implicit reward-variance regularization inherent to RFT, which proves incapable of suppressing uncontrolled optimization risk. We propose...
-
34
AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discovery
Zhijing Hu, Changjun Fan, Yufan Deng, Zhiguang Cao
cs.AI
Network dismantling is fundamental to analyzing the robustness and vulnerability of complex systems, yet practical heuristics must balance effectiveness and computational efficiency, and are usually designed manually by researchers. Existing large language model based automatic heuristic design methods can generate and screen candidates, yet they have difficulty further transforming candidate quality or failure states during execution into...
-
35
Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details
Maksymilian Wolski, Nicholas Hoernle, Johannes Forkel, Jakob Foerster
cs.AI · cs.MA
AI agents deployed in real-world settings must be capable of coordinating with humans and other AI agents they have not encountered before. Zero-shot coordination (ZSC) algorithms aim to achieve this by specifying high-level learning rules such that independently engineered agents can coordinate with each other at test time. Rigorous evaluation of ZSC algorithms remains difficult: ideally, multiple independent implementations of each proposed...
-
36
When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation
Yinuo Jiang, Yongjie Ye, Zhou Tao, Xiang Zhuang, Qiang Zhang, Huajun Chen, Tiankai Li
cs.AI
On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent selective OPD methods improve this process by prioritizing signals that are confident, informative, or learnable. However, the assumptions overlook a fundamental failure mode of language models: their token-level judgments can be driven by input-agnostic language priors, formatting conventions,...
-
37
Cross-Layer Interaction under Weight-Space Ablation: A Closed-Form Attention Jacobian Bound and a Test on a Real Pretrained Model
Abdallah Khemais
cs.AI · cs.LG
A companion paper studies when activation patching and weight-space ablation agree, inside an idealized model where a conditional computation is carried additively through a residual stream. For the one composition in that model where two carriers are architecturally dependent, an attention head and its own layer's normalization-MLP composition, it derives an exact first-order interaction formula, zero when only the MLP is ablated and...
-
38
Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detection
Razieh Chalehchaleh, Reza Farahbakhsh, Noel Crespi
cs.AI
Large Language Models (LLMs) are increasingly used for automated fact-checking, yet their susceptibility to gender bias in this context remains underexplored. This study presents the first systematic investigation of gender bias in LLM-based fake news detection using real-world data. We augment the LIAR benchmark with three gender variants of speaker job titles (Neutral, Male, Female) for each statement to test whether veracity judgments vary...
-
39
Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
Chunlei Meng, Jacqueline J. Pang, Pengbin Feng, Zhenyu Yu, Chun Ouyang, Zhongxue Gan
cs.AI · cs.MM
Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete. Existing methods for incomplete-observation MSA mainly follow two paradigms. Reconstruction-based methods recover missing information from observed modalities, while joint-representation methods learn directly from incomplete inputs. Although effective, these methods usually treat modality...
-
40
Formal Verification of Agentic Systems over Operational Data
Alejandro J. Mercado, Alessio Lomuscio
cs.AI
Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data. Before deployment, these systems need to be verified against business requirements that govern workflow execution and data evolution. However, existing approaches do not provide such system-level guarantees, as they mainly constrain or analyse behaviour at the agent's interface level. We study...
-
41
Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents
William Bolton, Philip Torr
cs.AI · cs.LG
Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence. We study this setting by framing oncology clinical development as an offline decision-making problem in which an agent predicts the next six-month trial portfolio of an oncology drug program from information available at the decision date. To support this, we construct a temporal dataset that...
-
42
FraQ: Efficient Coordinate-Space Recompression for Federated Low-Rank Adaptation
Shenghui Li, Thiemo Voigt
cs.AI
Federated fine-tuning with Low-Rank Adaptation (LoRA) enables efficient collaborative adaptation of Large Language Models (LLMs) without centralizing private data. However, LoRA's two-factor parameterization creates an aggregation mismatch across clients: naively averaging the factors does not recover the average of their induced updates. This mismatch can be avoided by forming the exact aggregate in the full weight space and then...
-
43
Large language models for partial differential equation workflows
Han Wan, Rui Zhang, Hao Sun
cs.AI
Partial differential equations (PDEs) become actionable in science and engineering not as isolated formulae, but as executable workflows that connect modelling assumptions, governing equations, numerical solvers, diagnostics, and decisions. Large language models (LLMs) are beginning to support such workflows by linking natural language, symbolic mathematics, code, solver outputs, and feedback. Here we examine recent advances in LLM-assisted...
-
44
FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection
Amirhossein Taleshinosrati, Yangyang Wang, Atitaya Phoemsuk, Vahid Abolghasemi, Naser Hossein Motlagh, Sadasivan...
cs.AI · cs.LG
Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and is associated with increased risks of stroke, heart failure, and mortality. Recent ECG foundation models offer transferable representations for automated AF detection. However, their relative effectiveness remains unclear because existing studies use different datasets, preprocessing procedures, classifiers, and validation protocols. This study presents FOUND-AF, a...
-
45
From Social Coding to Agentic Coding: Productivity and Relational Reconfiguration in Open-Source Communities
Mengying Zhou, Yongjie Yin, Yang Chen
cs.AI · cs.CY
Open-source software communities are a form of digital public infrastructure that not only produces code, but also generates public knowledge and interpersonal relationships through visible collaboration. Generative coding agents (CAs) are an advanced tool to improve development efficiency while shifting part of activities from public human interaction to private human-agent loops. We study this shift using an LLM-based multi-agent simulation...
-
46
Policy Fragmentation or Institutional Alignment? Institutional Governance of AI in Universities and Business Schools
Lydia Manikonda, Dominique Outlaw
cs.AI · cs.CE · cs.ET
Artificial intelligence (AI) is rapidly transforming high-skilled domains, requiring higher education institutions (HEI) to balance the teaching of foundational principles with the integration of emerging tools to ensure workforce readiness. While HEI are increasingly adopting AI, many continue to grapple with how it should be incorporated into curricula and governed through policy, especially when such policies are set at different levels of...
-
47
Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities
William Bolton, Philip Torr
cs.AI · cs.CY · cs.LG · cs.MA
Benchmarking the ability of AI scientists to generate novel ideas is notoriously difficult. Existing benchmarks in this field have made progress in evaluating scientific reasoning and research replication, but often rely on synthetic tasks or retrospective targets, which may be confounded by prior exposure. We hypothesize that complex, adversarial, fast-moving real-world domains where expert practitioners independently generate observable...
-
48
Enhancing Tabular Learners with Context-Aware Semantic Embeddings
Günther Schindler, Maximilian Schambach, Johannes Höhne
cs.AI · cs.LG
While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries. We propose CASE (Context-Aware Semantic Embeddings), a novel framework that bridges the gap between the semantic understanding of Large Language Models (LLMs) and the statistical capabilities of tabular...
-
49
Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve
Denys Pushkin, Albert Q. Jiang, Aryo Lotfi, Colin Sandon, Emmanuel Abbé
cs.AI
Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to elicit step-by-step reasoning from large language models (LLMs), which would otherwise tend to directly output the final answer. However, many modern LLMs produce CoT-style responses \textit{natively} when presented with reasoning tasks, which made us revisit the effectiveness of standard CoT...
-
50
Behaviorally Adaptive Visual Diversion for Inclusive and Resilient Digital Assessment Delivery
Gupta Lovi Raj, kaur Kamalpreet, Dama Sriram, Parali Prajithaa
cs.AI · cs.CY
Institutions increasingly rely on browser lockdown, webcam monitoring, and behavioral analytics to secure high-stakes digital assessments, yet these mechanisms are commonly designed and evaluated independently and often overlook learner accessibility. This paper introduces Behaviorally-Adaptive Visual Diversion (BAVD), a theoretical framework in which a synthetic, non-semantic visual field is composited with assessment content and adaptively...
-
51
Dr. AGENTONOMICS: A Didactic Experiment of AGENTONOMICS
Fengjunjie Pan, Alois Knoll
cs.AI
AGENTONOMICS is a framework that treats AI agents as economic entities that can be designed, managed, and governed through an integrated management architecture. Dr. AGENTONOMICS is its first application: a lecture agent developed in the context of the TUM course on AI agents in business administration. Conceived during the winter semester 2025/26 and first introduced to students in the summer semester 2026, it serves as a didactic experiment...
-
52
Reversing Arrows in Large Language Models
Sefika Efeoglu, Adrian Paschke
cs.AI
Large language models (LLMs) have achieved strong performance on text-to-knowledge graph generation and related tasks. Nevertheless, it is still unclear whether they accurately model the direction-dependent semantics of inverse relations, in which reversing the order of the arguments alters the meaning of a relation (e.g., \textit{mother} versus \textit{child}). To the best of our knowledge, this work presents the first systematic study of...
-
53
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague, Fangcong Yin, Nhat Ho
cs.AI · stat.ML
Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal...
-
54
Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks
Christophe D. Hounwanou, John Emeka Eze, Yaé Ulrich Gaba
cs.AI · cs.LG · cs.MA
Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However, LLM-based agents struggle with long-horizon sequential decision tasks that require precise action optimization and environment interaction. Reinforcement Learning (RL), while effective for sequential control, often lacks the high-level abstraction and task decomposition abilities needed...
-
55
Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Design
Zejun Liu, Jian Wu, Ru Peng, Yuliang Ji, Dongyuan Li, Renhe Jiang, Yue Zhang
cs.AI
AI for Research (AI4Research) leverages AI to automate and improve scientific workflows. While experimental design is a critical stage of the research process, prior work has focused primarily on code implementation and execution, overlooking the importance of this stage, and no benchmark exists to evaluate AI's ability to conduct systematic experiment design. To bridge this gap, we propose SCOPE, a Scientific COmprehensive Planning...
-
56
WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
Prince Zizhuang Wang, Aojie Yuan, Haiyue Zhang, Xiyang Hu, Yue Zhao, Shuli Jiang
cs.AI
Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not...
-
57
ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning
Xiuhui You, Jiayi Luo, Zichao Shen, Qingyun Sun, Ziwei Zhang
cs.AI
Historical tool-use trajectories provide valuable experience for large language model (LLM) agents to plan and coordinate tool usage. Existing approaches directly construct tool-level graphs from these trajectories, but the resulting graphs remain tied to specific tools and are hard to generalize across tool sets. To tackle this challenge, we find that despite differences in the tools involved, analogous tasks often share a common...
-
58
When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO
Zhe Cao, Miaowen Wen, Fangjiong Chen
cs.AI · cs.LG
Reinforcement learning with verifiable rewards (RLVR) com- monly optimizes each correct completion as an independent learning signal. In GRPO, this completion-level uniformity creates structure-level skew: recurring correct solution forms accumulate positive coefficient mass in proportion to how often they are sampled, while rare forms receive limited credit. We formalize this behavior as multiplicity-induced structure-level credit...
-
59
ChartAnno: Evaluating MLLMs for Chart Annotation Generation
Zhenghan Chen, Zekai Shao, Lidan Tan, Xin Lin, Xingchen Zeng, Yi Shan, Ziyue Lin, Xiaoliang Fu, Xinyuan Liu, Yuetong...
cs.AI · cs.CL · cs.HC
Multimodal large language models (MLLMs) have made significant progress in chart understanding, generation, and editing, but their ability to annotate existing charts remains underexplored. Annotating charts is a common yet challenging communicative task, requiring models to infer intended messages, interpret chart semantics, and place appropriate textual or graphical elements. To address this gap, we introduce ChartAnno, a benchmark for...
-
60
LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
Yuxin Liao, Le Wu, Min Hou, Hao Liu, Han Wu, Zishu Wang
cs.AI
Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typically process heterogeneous dialogue content through a uniform summarization and retrieval pipeline, leading to either excessive token consumption or irreversible loss of fine-grained evidence. We argue that historical dialogue content should be handled differently according to its...
-
61
Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
Janis Zenkner, Tobias Sesterhenn, Tim Grams, Christian Bartelt
cs.AI
Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermediate subgoals, and a synthesizer generates programs conditioned on them. Current approaches train the decomposer to imitate ground-truth ( GT) subgoals, implicitly treating decomposition quality as intrinsic to the task. We challenge this assumption: for bounded solvers with...
-
62
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models
Fengqi Zhu, Shaoxuan Xu, Jingyang Ou, Zebin You, Yipeng Xing, Huabin Liu, Xiaolu Zhang, Jun Zhou, Zhenzhong Lan,...
cs.AI
Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dLLMs remains poorly understood. We systematically characterize how optimization hyperparameters, compute allocation, and architecture scale for MoE dLLMs, identifying quantitative differences from scaling trends previously reported for AR models. Specifically, for optimization, the optimal...
-
63
DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
Boyan Li, Zhuowen Liang, Yupeng Xie, Xiaotian Lin, Tianqi Luo, Xinyu Liu, Yizhang Zhu, Zhangyang Peng, Yuan Li,...
cs.AI
Data agents enable natural-language analytics over organizational workspaces, where relevant evidence may be scattered across databases, structured files, long documents, and multimedia. Existing benchmarks largely isolate structured querying, retrieval, or open-ended analysis, leaving heterogeneous evidence discovery, complete tabular outputs, and deterministic evaluation insufficiently unified. We introduce DataSpace, a benchmark in which...
-
64
State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking
Xiaohe Li, Yang Lu
cs.AI
Transformer-based architectures have dominated sequence modeling, largely due to the expressive power of attention mechanisms. However, for a class of deterministic state tracking tasks---such as parity checking, modular counting, and parenthesis matching---attention may be overkill. In this paper, we show that \textbf{state propagation alone is sufficient}. We propose the \textbf{Complex State Propagator (CSP)}, a minimalistic recurrent...
-
65
Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory
Jakub Rada, Viliam Lisý
cs.AI
Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood. We study this on fully-observable two-player zero-sum games, which provide ground-truth evaluation: outcomes are determined by the rules, and optimality of individual moves can be computed or approximated, without relying on a judge model. Across model tiers, LLMs play suboptimally in...
-
66
AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction
Jonaid Shianifar, Iias Faiud
cs.AI · cs.LG
Large language models (LLMs) are now regularly asked to forecast real-world events, but comparisons are often difficult because models receive different information, use different tools, and are evaluated under different rules. This paper reports the completed \emph{AI World Cup} benchmark, in which ten LLM-based assistants made a single pre-tournament forecast of the entire 2026 FIFA World Cup. Every submission used the same tournament...
-
67
Enactive Artificial Intelligence: A Decision-Centric Architecture for Complex Systems
Zuojun Max Shen, Yuan Qu, Pujun Zhang, Anbang Liu, Yunhao Liang
cs.AI · cs.ET
As artificial intelligence (AI) continues to evolve and mature, recent AI practices have moved beyond large language models (LLMs) and text or image generation tasks, increasingly integrating tools, agents, and harnesses to solve real business and industrial problems. However, the power of AI is not verified under these real-world complex systems for various reasons, considering reliability, feasibility, resilience, and responsibility...
-
68
Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance
Can Wang, Haoran Chen, Li Yu, Ding Hao, Bohai Zhao, Zhaoyang Liu, Zhiying Tu
cs.AI
The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes. Tools play a central role as the primary interface through which agents interact with external environments, yet existing methods rarely focus on ensuring robust tool use across diverse runtime conditions. To address this problem, we propose ExpG, a mechanism that builds and refines adaptive guidance capturing...
-
69
MMLongBench-Doc-V2: A Corrected-Annotation, Semantics-Aware Revision of MMLongBench-Doc
Mingtian Zhang
cs.AI
MMLongBench-Doc is a long-document QA benchmark of 1,082 questions over 135 PDFs. Two properties of it push measured scores away from the quantity they are meant to capture: the reference metric compares extracted answers, so 1,358,000 loses to 1358000; and a non-trivial share of ground-truth annotations are wrong, ambiguous, or incomplete --- concentrated, because of how they were found, in exactly the questions capable systems answer...
-
70
Traceable Multi-Agent System for Knowledge-Based Forecasting
Junhyeok Kang, Sangjun Han, Hyeokjun Choe, Soonyoung Lee
cs.AI
Enterprise forecasting increasingly relies on autonomous agents that interpret documents, search for data, generate code, and revise models. While this autonomy helps build adaptive forecasting pipelines, it also makes it difficult for practitioners to inspect why a forecast changed, which evidence supported the change, and how data and modeling choices were revised. We present TraceMAS, an interactive demo system for traceable multi-agent...
-
71
Long-term Traffic Scene Prediction via Polynomial Representations in Autonomous Driving
Yue Yao
cs.AI
This thesis addresses fundamental challenges in traffic scene prediction for autonomous driving by introducing robust and computationally efficient models based on polynomial representations. While conventional sequence-based representations often struggle with noise and generalization, this work demonstrates that polynomial representations offer significant advantages in computational efficiency, generalization, and prediction plausibility....
-
72
Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
Siqi Fan, Minghao Li, Xiaoqian Ma, Wenhui Tan, Xiusheng Huang, Juntong Wu, Liujie Zhang, Shuo Shang, Weihang Chen
cs.AI
Hybrid computer-use agents can act through screenshots or call text tools. We find that having a tool available does not settle which way the effect goes. Under one identical GUI-MCP harness on the OSWorld-MCP benchmark (309 tasks), the same MCP tools improve a reasoning model by +4.0pp and degrade a non-reasoning model by -5.9pp (5 runs each, both beyond 2 SE). What separates the two is tool-decision behavior. The non-reasoning policy...
-
73
SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation
Shengjun Fang, Chenyang Wu, Zongzhang Zhang
cs.AI
Agentic presentation generation must preserve source content, maintain coherent visual design, render specialized objects, and produce usable artifacts. Existing systems meet only part of this requirement: templates preserve regularity but restrict adaptation, whereas free-form HTML or SVG gives models flexibility at the cost of low-level rendering decisions. This mismatch makes long technical decks brittle, especially when slides contain...
-
74
Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks
Mohsen Arjmandi
cs.AI · cs.CL
A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant information is preserved. We test this claim by running every sample of two long-context benchmarks -- BABILong and GraphWalks (BFS) -- at four context-retention fractions (100%, 75%, 50%, 25%) under two truncation protocols. The first is the naive protocol implicitly used in much prior work: drop...
-
75
DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning
Le Xiang, Zhicheng Guan, Hong Chen, Xiaocong Lin, Zhenghua Lei, Teng Hu, Bolei He, Long Zeng
cs.AI
Long Document Visual Question Answering (LongDocVQA) requires Multimodal Large Language Models (MLLMs) to locate, integrate, and reason over heterogeneous document elements distributed across multiple pages. Existing approaches, including end-to-end MLLMs, retrieval-augmented generation (RAG) pipelines, and document agents, often lack explicit mechanisms to represent and verify how grounded evidence is progressively composed during reasoning,...
This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.