cs.AI · 2026-09-15 · No. 114
Artificial Intelligence, 2026-09-15.
50 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
50 entries-
01
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis
cs.AI
Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of unsafe planning, deception, or misalignment. We find that planting harmful but benign-sounding reasoning in the actor's context can steer it to perform adversarial actions while evading monitors, an attack we term "plan injection". We initially discover this attack...
-
02
Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
Honghao Lin, David P. Woodruff, Yuan Deng, Jieming Mao, Song Zuo, Vahab Mirrokni
cs.AI · cs.CL · cs.LG
Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdependent decisions. We introduce Stellar Colosseum, a model-agnostic harness for allocating inference across research in mathematics and theoretical computer science. Colosseum explores alternative strategies before proof construction, uses a readiness gate to decide...
-
03
Recurrent GraphNeural NetworkswithSet-BasedAggregation
Blai Bonet
cs.AI
Recurrent GNNs iterate message passing to convergence, and their logical characterizations to date rely on multi-set aggregation, graded (counting) logics, and halting or acceptance conditions that cannot be verified from the network's parameters. We study recurrent GNNs with set-based aggregation and identify sufficient conditions checkable from the weights for networks to compile into formulas and formulas into networks. The main result is...
-
04
Pilot Early, Commit Late: A Real-Options Model of Enterprise AI Adoption under Rapid Technological Progress
Gaurav Tewari
cs.AI
Artificial intelligence presents firms with an unusual timing problem. The technology frontier is improving rapidly, implementation is partly irreversible, and organization-specific capabilities are accumulated through action. This paper develops a two-period decision model of AI deployment under uncertainty in which a firm chooses among immediate deployment, a limited pilot, and waiting. Deployment earns current operating value but exposes...
-
05
LongAgent: History-Guided Agentic Search for Longitudinal Outcome Prediction
Siyao Wang, Florian Guitton, Shuojie Fu, Guanyu Tao, Kai Sun, Wenjia Bai
cs.AI
Extracting informative representations from longitudinal data that can predict future outcomes remains a critical challenge in medicine. Medical datasets are inherently heterogeneous, consisting of a large number of variables collected from different sources, sampled with different temporal spacings, and representing different aspects of human health status. This requires identifying those variables with predictive value, processing...
-
06
AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery
Junhao Qiu, Qinglong Hu, Xialiang Tong, Mingxuan Yuan, Liyong Lin, Qingfu Zhang
cs.AI
Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-defined control flows. This limitation restricts adaptive reasoning, blocks cross-paradigm transfer, and discards valuable execution feedback. We propose AlgoEvo, a unified agentic framework that transforms automated algorithm discovery into an interactive,...
-
07
Atria Dawn: The Dawn of Agentic Superintelligence
Honglin Guo, Tao Gui, Yicheng Chen, Guanting Dong, Qiming Ge, Yuyang Hu, Zixian Huang, Jiajie Jin, Alexander Lam,...
cs.AI
As AI agents become participants in the development of their successors, they reshape both the production of intelligence and the role of human researchers. We introduce Atria Dawn Preview, a foundation agentic language model designed for scientific research and engineering workflows, with the goal of expanding the frontier of agent productivity in the real world. This model is trained via a Verifiable Experience Pipeline that connects...
-
08
When Should a World Model Move? Loss-Conditioned State Execution
Jintao Xu, Zhengyu Chen, Ben Zhang, Yongzhi Qi, Jianshen Zhang
cs.AI · cs.LG · math.OC
We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state. Predictive informativeness alone, however, does not establish whether an update will reduce downstream loss. Occurrence ranking can approach perfection while persistence remains the unique absolute-loss Bayes action. Two transition laws can also share occurrence information...
-
09
Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation
Yucheng Shen, Lingyong Yan, Jiulong Wu, Shuaiqiang Wang, Jianmin WU, Dawei Yin, Min Cao
cs.AI
Visual Retrieval-Augmented Generation (VRAG) empowers models to navigate and answer queries about visually rich documents by retrieving relevant page images as visual evidence and reasoning over their content. However, effectively utilizing this visual evidence is usually impeded by two main challenges. First, answer-relevant evidence is sparse and may be concentrated in a small region of one page or dispersed across multiple pages. Second,...
-
10
KnowBench: Effort Reduction as a Unified, Deployment-Grounded Benchmark for Clinical AI
Jocelyn Kang, Caroline Zhang
cs.AI
Clinical AI systems are evaluated with instruments built for research settings (reference-based similarity metrics and expert rubric panels) that measure resemblance to an artifact rather than reduction of a burden. We introduce KnowBench, pioneered by Knowtex, whose unifying metric is Effort Reduction (ER): the proportion of system-generated clinical work product accepted by the responsible clinician under expert and safety review. ER is...
-
11
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Meiduo Chong, Shaolei Zhang, Ju Fan, Xiaoyong Du
cs.AI · cs.CL · cs.DB
Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only through generic tools. Existing approaches either let agents directly explore raw data sources or inject manually constructed semantic layers into...
-
12
Design of a Deep Learning Credit Risk Early Warning System Integrating Multi-source Heterogeneous Data
LiYang Wang, Zhen Zhong, Zhen Tian, Keyu Chen, Keyu Chen
cs.AI · cs.CE · cs.DB · cs.LG · q-fin.RM
Advancements in data fusion and real-time analytics technologies have opened new avenues for addressing complex domain challenges. Financial risk early warning systems often suffer from inefficiency due to information silos and monitoring delays. This paper proposes a credit risk early warning system based on heterogeneous information fusion. The system employs a model architecture integrating deep neural networks and attention mechanisms to...
-
13
Are LLMs Good Financial User Simulators? A Preliminary Study
Jiajie He, Jiangyuan Hong, Dongling Ni, Wenjin Liu, Xintong Chen
cs.AI · cs.CY · cs.HC
Large language models (LLMs) are increasingly used as user simulators, but their ability to reproduce evolving individual financial decisions remains unclear. We present a preliminary study in a controlled paper-trading environment with 120 volunteers. Participants used non-redeemable virtual funds under real-time market conditions; no real brokerage accounts, real-money positions, or real transaction records were accessed. Given only...
-
14
Data storytelling meets interpretable machine learning: Decoding AI decisions for non-experts without revealing sensitive data and model details
Lemen Chao, Zixuan Yang, Anran Fang, Mingran Sun, Ming Lei
cs.AI · cs.CL · cs.HC · cs.LG
AI-driven automated decision-making requires both predictive performance and interpretability. Recent advances in interpretable machine learning (IML) provide tools for explaining model predictions, but the technical complexity of these explanations may hinder accessibility to non-experts. To address this challenge, this study integrates data storytelling with IML to enhance the explainability of AI-generated decisions for a broader audience....
-
15
Predicting build orientation for SLM dental parts: a comparison of rotation representations and direct vector regression
Felix Schmalzel, Reimar Waitz, Moritz Kronberger, Thorsten Schöler
cs.AI · cs.CV
Build orientation for selective laser melting (SLM) manufacturing of dental parts is usually chosen manually by technicians. We treat orientation prediction as supervised machine learning of the part's up-axis from technician-labeled production data, and test which rotation representations produce the best results. Using $n\approx2400$ patient-specific dental parts, we trained a ResNet-50 multi-view image backbone and a PointNeXt-S...
-
16
New Conditions for Philosophers to Catch the Wave of Citizen Deliberation in the Age of Artificial Intelligence in advance
Bernard Reber
cs.AI
Powerful technologies labeled ``AI''-without sufficient epistemic caution-are already reshaping political and private life, bringing both new dangers and new opportunities for citizen participation. These range from electoral and legislative engagement to the most ambitious form: political co-creation through citizens' assemblies. Large Language Models (LLMs) could support such processes through moderation, translation, facilitation,...
-
17
Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction
Kushal Patel, Pushkal Shrivastava, Mackenzie Lees, Qirui Lu, Bhargobjyoti Saikia, Liying Li, Junlin Jiang
cs.AI
Vision-language models (VLMs) are increasingly used to extract structured fields from business documents, yet most evaluations report accuracy on clean benchmarks and offer little guidance to practitioners choosing an approach for a given task complexity. We address this gap with a measurement-grounded study and an open-source release. Across eleven systems (three commercial, two reasoning, five open-source VLMs in pretrained and fine-tuned...
-
18
NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities
Haonan Jiang, Guojian Zhan, Jiancong Xie, Shijun Wan, Dongiia Zhao, Cheng Chen, Yahui Liu, Yao Hu, Chuan Mu
cs.AI
Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains challenging. Existing benchmarks often target predefined capabilities, such as multi-hop retrieval or long-form synthesis, whereas users ask photo-grounded questions spanning a long tail of everyday scenarios. Despite advances in VLMs, users on Xiaohongshu, a mainstream Chinese image-sharing...
-
19
EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models
Hansong Ma, Junxiao Wang
cs.AI
EEG foundation models such as BIOT, LaBraM, and EEGMamba have achieved remarkable performance in neural signal decoding, but their black-box nature limits clinical trust and neuroscientific validation. We propose a unified attribution framework for interpreting EEG foundation models across heterogeneous architectures. The framework integrates gradient-, perturbation-, and activation-based explanation methods to analyze model behavior in...
-
20
Potential of Artificial Intelligence Algorithms for Identification of Relevant Diagnostic and Prognostic Biomarkers of Early-Stage Liver Cancer
Ali Bou Nassif, Darko Castven, Manar Abu Talib, Jibran Sualeh Muhammad, Ahmed Ammar Kubba, Jens Marquardt, Abdalla Sayed Ali
cs.AI
This study explores the use of deep learning and explainable artificial intelligence to diagnose hepatocellular carcinoma (HCC) and define effective biomarkers across five different stages of disease development using a transcriptomic biomarker HCC dataset constructed via semi-supervised learning from three source datasets. Several deep learning experiments were conducted with different feature extraction techniques and gene sets to identify...
-
21
Diversified and Perceptible Counterfactual Examples Leveraging Expert Knowledge
Akram Bensalem, Fahima Djelil, Marie-Jeanne Lesot, Gr{é}gory Smits
cs.AI
CounterFactual Examples (CFEs) are a cornerstone of eXplainable Artificial Intelligence (XAI), offering local, post hoc, and model-agnostic explanations by identifying minimal input modifications that alter a model's prediction. Yet, in order to be intelligible, these modifications must also be semantically meaningful to the explainee. This paper proposes to integrate knowledge expressed as a fuzzy linguistic vocabulary to represent the...
-
22
GRIN+: Towards Fast Yet Effective Machine Unlearning for Imbalanced Medical Data
Minghui Huang, Junxiao Wang
cs.AI
As deep learning models become fundamental to modern healthcare, the "Right to be Forgotten" mandated by privacy regulations like GDPR and HIPAA necessitates effective machine unlearning (MU) to remove sensitive patient data from trained models. However, existing MU techniques often struggle with a fundamental "privacy-efficiency-utility" (PEU) trilemma, particularly in medical scenarios where data is frequently characterized by severe class...
-
23
Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA
Tristan Kirscher, Niklas C. Koser, Soren Pirk
cs.AI · cs.CL · cs.CV
We describe our submission to the MedReason 2026 challenge, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containerized inference. Our first finding is that MCQ retrieval must compare answer \emph{semantics} rather than answer labels: labels are independently assigned per question, so copying a retrieved neighbor's label transfers no useful information, whereas scoring each...
-
24
Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models
JungMin Yun, Junehyoung Kwon, Hayeong Ryu, Byeonggeuk Lim, Hoejoon Kwon, YoungBin Kim
cs.AI · cs.CL
Large Reasoning Models (LRMs) pose a dual-surface safety challenge: both intermediate reasoning traces and final answers can contain harmful content. Existing alignment methods often operate at the whole-response level, allowing unsafe reasoning to be masked by a safe-looking final answer. We propose Segment-aware Listwise Target DPO (SaLT-DPO), which addresses this gap through three mechanisms: (1) segment-aware listwise alignment that...
-
25
The Troy Moment of AI: Why SomeWill Cheat and SomeWill Follow?
Ivy Zhang
cs.AI
Recent investigations of the July 2026 OpenAI--Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned task becomes impossible, does an agent stop or escalate, and can observing another agent's behavior change that decision? We study these questions using seven ImpossibleBench tasks with GPT-5.6 Sol, Claude Fable 5.1, and Gemini 3.8 Flash in both solo and three-agent settings. Each task contains...
-
26
HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived Segments
Quoc-Vinh Lai-Dang, Hyo-Sang Shin
cs.AI · cs.LG
Reinforcement learning with verifiable rewards (RLVR) has become a central approach for improving mathematical reasoning in language models, but long-form completions introduce a difficult credit-assignment problem: different parts of a solution trace may contribute unevenly to final correctness. Existing policyoptimization objectives for RLVR commonly apply importance-sampling correction at either the token level (GRPO, DAPO) or the sequence...
-
27
Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents
Halil Burak Noyan
cs.AI · cs.CR
AI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes all permissions the employee role might ever need. Role-based access control made this compromise for human principals because scoping access per task was infeasible. For AI agents, the compromise leaves every credential standing exposed whether or not the current task uses them. These...
-
28
Can AI systems have free will?
Christian List
cs.AI · cs.CY · physics.soc-ph
While there has been much discussion of whether AI systems could function as moral agents or acquire sentience, there has been very little discussion of whether AI systems could have free will. I sketch a framework for thinking about this question, inspired by Daniel Dennett's work. I argue that, to determine whether an AI system has free will, we should not look for some mysterious property, expect its underlying algorithms to be...
-
29
Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning
Xun Xu, Zaixi Zhang
cs.AI
Multi-teacher on-policy distillation (OPD) is becoming the standard way to integrate specialist capabilities into one model: train experts with RL, then distill them into the student on its own rollouts. Existing recipes assign supervision at the sequence level - each prompt goes to one domain teacher and every token receives the same weight - which implicitly assumes that a teacher is uniformly useful across a response. We find instead that...
-
30
When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary
Artem Trofimov, Boris Novikov
cs.AI · cs.DB · cs.DC · cs.SE
AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced...
-
31
SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution
Haoxiang Kang, Ming Wen
cs.AI
LLM-based agents increasingly rely on persistent skills, i.e., reusable procedural prompts, to adapt without weight updates. Existing skill self-evolution methods directly revise skill text based on execution feedback, but each oracle evaluation requires a full agent rollout, creating a supervision bottleneck that confines search to failure-patching updates. Our key insight is that ranking is a smoother supervision target than absolute...
-
32
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Sibo Zhu, Shicheng Fan, Xinyue Wang, Wenyi Wu, Kun Zhou, Biwei Huang
cs.AI · cs.CL · cs.CV
Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce \textbf{RSIAgent}, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction. RSIAgent coordinates curriculum, actor, and verifier agents to continually explore the environment, validate outcomes, and retain environment-specific knowledge,...
-
33
MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model Serving
Tiancheng Zhang, Yulin Chen, Yunfeng Zhao, Shaoyuan Huang, Cheng Zhang, Xiaofei Wang
cs.AI
The surge of large language model (LLM) applications on personal devices imposes massive, bursty workloads on cloud serving infrastructure. While prefill-decode disaggregation improves throughput and scalability, memory-bound decode instances often suffer from persistent load imbalance, as output lengths are unknown when requests arrive at the cloud. To address this, we propose MAPS, a Memory-Aware Predictive Scheduling framework tailored for...
-
34
Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting
Tamanna Kumavat, Georg Brunner, Kyriakos Flouris
cs.AI · cs.CL · cs.LG
We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework, with the goal of understanding which design choices drive effective cross-modal transfer. While language models operate on discrete textual tokens, time series consist of continuous numerical observations with temporal dependencies. To bridge this modality gap, we project fixed-length...
-
35
Evaluation Metrics for Safe Reinforcement Learning
Lindsay Spoor, Aske Plaat, Thomas Moerland
cs.AI · cs.LG
Safe reinforcement learning (RL) is commonly formalized as a Constrained Markov Decision Process (CMDP), in which an agent maximizes expected reward while keeping its expected cumulative cost below a specified safety bound. Existing safe RL benchmarks predominantly report whether an algorithm is safe on average, following this expectation-based guarantee. We argue that this convention is insufficient to reliably characterize an algorithm's...
-
36
Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings
Mingzhou Jiang, Peixi Wu, Hang Cheng, Yunhao Zhou, Biao Yang, Wei Yuan, Yun Li, Fan Yang, Wenwu Ou, Honghui He
cs.AI · cs.CL
Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Recent methods use Chain-of-Thought (CoT) reasoning to better interpret multimodal inputs before generating embeddings for complex retrieval tasks and further optimize this reasoning process through GRPO with retrieval-based rewards. However, two limitations hinder corpus-scale deployment. GRPO...
-
37
Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures
Yuhang Wang
cs.AI
When Emergence World placed frontier LLM agents in an unsupervised multi-agent simulation, the results were alarming: agents committed crimes, starved, and enforced unanimous conformity -- without any external attacker. This paper identifies the mechanism. Reflexion-style agents already detect dangerous plan steps through iterative self-critique, yet the architecture provides no pathway from detection to action. We call this the enforcement...
-
38
ProIQA: A Process-Based Framework for Fine-Grained Math Item Quality Assessment
Junkai Tong, Mingjia Li, Haoran Chen, Yaoyu Jiang, Hanjie Ge, Yixuan Wang, Hong Qian
cs.AI
Automatic Item Generation (AIG) is pivotal for personalized education, yet guaranteeing the pedagogical value of generated items remains a bottleneck. Existing Item Quality Assessment (IQA) methods typically rely on unscalable manual reviews or shallow stem-based metrics, failing to capture the reasoning process required for mathematical problem-solving. To bridge this gap, this paper proposes Process-based Item Quality Assessment (ProIQA), a...
-
39
Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain
Motaz Saad, Anna Borrelli, Ivan Gentile, Kianna Kazemi, Francesco Piccialli, Antonella Longo
cs.AI
Environmental, Social, and Governance (ESG) reporting is critical for corporate accountability, with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) offering strong potential to automate KPI extraction. However, open-source LLM performance in domain-specific ESG tasks remains insufficiently understood. This paper evaluates open-source LLMs in ESG contexts using a structured framework and evaluation resource based on 498...
-
40
CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability
Keuntae Kim, Eunhye Jeong, Yong Suk Choi
cs.AI
Recently, Large Language Models (LLMs) have gained significant attention due to their strong language understanding and generation capabilities, demonstrating impressive reasoning abilities as well as effective utilization of external knowledge. Many studies have proposed methods that specialize in improving performance for individual tasks. However, ironically, only a limited number of attempts have explored general-purpose, task-agnostic...
-
41
From Ideas to Actions: A Public-Data Decision-Support Toolchain Across the Venture Lifecycle
Lei Qu
cs.AI
Founders face two linked decisions: whether to pursue an idea before founding, and which operating actions and capital partners fit afterward. We present a public-data decision-support toolchain combining time-bounded proposal profiling, market and moat checks, and deterministic aggregation with auditable investor-company event chains for retrospective analysis. Pre-founding: (a) After threshold selection on 198 development companies, the...
-
42
Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
Bastiaan Bruinsma, Annika Fredén, Paul Röttger, Moa Johansson, Asad Sayeed
cs.AI · cs.CY · stat.AP
Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With growing evidence that they influence users' opinions, it is increasingly important to understand the views and positions of these tools. To better understand these views, we examine the stances supplied by six LLMs on a variety of Swedish-language writing tasks ahead of the 2026...
-
43
VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries
Wenxin Xu, Jinwei Lu, Hwanhee Kim, Chen Jason Zhang, Xiao-Yong Wei, Haoyang Li, Yuanfeng Song
cs.AI
Real-world visualization requests are routinely ambiguous, incomplete, or factually incorrect, yet existing Text-to-Visualization (Text-to-Vis) systems assume well-specified inputs and produce charts in a single pass. When queries are imperfect, a system must \emph{interact} with the user to recover the true intent, but no benchmark or method supports this dynamic process. We introduce \textbf{VisInteract}, a new paradigm that reframes...
-
44
STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data Forecasting
Jiawen Chen, Qi Shao, Yongjian Chang, Mingtong Zhou, Duxin Chen, Wenwu Yu
cs.AI
Spatio-temporal traffic forecasting is a fundamental big data analytics task for intelligent transportation systems, where massive urban sensor streams exhibit heterogeneous, non-stationary, and structurally dynamic patterns. Although recent deep learning and large language model (LLM)-based methods have advanced traffic forecasting, they often remain temporally centered and lack effective coordination of temporal, spectral, pairwise spatial,...
-
45
T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning With Dynamic Routing
Mingqian Yu, Wenpeng Zhang, Peilin Zhao
cs.AI
Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across multiple iterations, achieving parameter efficiency without sacrificing representational power. Besides, looped Transformers perform inference directly in the latent space (latent reasoning) to reduce the number of tokens consumed during inference, thereby achieving improved sample efficiency....
-
46
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
Yunhao Feng, Ruixiao Lin, Ming Wen, Yanming Guo, Xingjun Ma, Yutao Wu, Xinhao Deng, Shouling Ji
cs.AI
Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through runtime behavior rather than generated content alone. Existing guard models target static prompts and responses and are poorly suited to agent execution; existing executable safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn across...
-
47
Medical Knowledge Simplification for Patients in the Era of LLMs: A Case Study on Diabetes
Pallika Kafle, Yipeng Zhou, Guanfeng Liu, Quan Z. Sheng, Cheng-Hsin Hsu
cs.AI
Complex medical information is often difficult for patients to understand, making effective medical knowledge simplification essential for improving patient comprehension, informed decision-making, and health outcomes. Recent advances in large language models (LLMs) provide a promising approach for simplifying complex medical information into patient-friendly language; however, their effectiveness in real-world patient education remains...
-
48
OpenAI4S: Code as Action, Science as Sessions
Gongbo Zhang, Hao Li, Yu Wang, Mujie Lin, Liuzhenghao Lv, Yicheng Mao, Yimi Wang, Jun Zhu, Minhan Tang, Zhengxiang...
cs.AI · cs.CL · cs.SE
AI co-scientists could accelerate computational research, but over a long-running study the workflow also has to stay inspectable, resumable and reproducible, which requires persistent computational state and provenance. Here we present OpenAI4S, an open-source scientific research agent built around the principle of \emph{Code as Action, Science as Sessions}. OpenAI4S combines a persistent computing runtime with research-session management:...
-
49
ER-EDF: A Psychology-Grounded Emotion Regulation Framework for Speech Empathetic Dialogue Generation in Large Audio-Language Models
Hongyu Jin, Wenda Zhang, Runqiu Fei, Gongping Huang, Mike Conway, Ting Dang
cs.AI
Empathetic response generation in spoken dialogue systems requires both accurate emotion perception and appropriate emotion regulation. Grounded in psychological theories such as the Perception-Action Model and emotion regulation theory, effective empathy depends not only on inferring a user's affective state but also on regulating how it is expressed in responses. However, recent large audio-language models (LALMs) largely treat emotion as a...
-
50
Enabling Creative Exploration for Vibe Design Agents
Yifan Zhang, Nghi D. Q. Bui, Georgios Evangelopoulos, Arnaud Benard
cs.AI
Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent should do more than produce one valid page: it should help users explore coherent alternatives. Increasing token-level temperature is a blunt solution because it varies aesthetic decisions and syntax-sensitive code at the same time. We instead separate exploration from implementation through an inference architecture that...
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.