cs.AI · 2026-08-12 · No. 82
Artificial Intelligence, 2026-08-12.
51 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
51 entries-
01
Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
Alan Li, Rahul Saha, Anton Xue, Swarat Chaudhuri, Adam Klivans, Pravesh K Kothari, Raghu Meka
cs.AI · cs.CC · cs.HC · math.FA
AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck constant $K_G$, which captures the hardness between combinatorial problems and their continuous relaxations. Specifically, while the precise value of $K_G$ is not known, we recently tightened the best known bounds to \[...
-
02
sLTN: Structural Logic Tensor Networks
Davide Rinaldi, Luciano Serafini
cs.AI
Logic Tensor Networks (LTN) provide a neurosymbolic framework in which first-order logic is interpreted through tensor operations, enabling logical constraints to be integrated with differentiable learning. However, the original formulation of LTN is primarily suited to data represented as flat collections of individuals, and does not explicitly capture structural organization such as temporal order, sequential position, or graph...
-
03
Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
Kushal Chakrabarti
cs.AI · cs.LG · cs.SE
Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace this to imperfect recall: appending an instruction is always cheap, but once an instruction's rationale is gone, deleting it without risking a correctness regression costs O(2^|D|) in a prompt of |D| instructions. We name the resulting divergence catastrophic remembering, the...
-
04
RTSKG: Building a Rail Transit Station Knowledge Graph Dataset
Shutong Zhu, Tianxing Wu, Runfeng Liu, Yuang Gu, Xuan He, Yuan Zhu
cs.AI
Rail transit systems play a vital role in urban mobility and economic development. As key components of such systems, rail transit stations function as critical transport hubs that enhance urban accessibility and stimulate development in surrounding areas. City-level rail transit station related tasks (e.g., ridership prediction) require large-scale urban data, but current studies often neglect complex interactions among various urban...
-
05
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
Xiaofan Bai, Hongqiang Lin, Chao Liu, Yantao Zhang, Xuan Jin, Xipeng Cao, Yuhong Li
cs.AI
Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. The resulting skill becomes expensive to inject and difficult to maintain. Generic prompt compression is ill-suited to this setting because a skill is not a flat passage: its name and...
-
06
V-FiLLM: Verified Financial LLM Reasoning Benchmark
Alicia Larsen, Victoire Laurent, Aulia Kharis Rakhamsari, Lara Turgut, Nino Antulov-Fantulin
cs.AI · cs.CE · cs.LG
While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains comparatively less explored. We introduce V-FiLLM, a framework that generates financial reasoning benchmarks from executable computation trees grounded in real tables, yielding items whose answers are correct by construction. Trees are evaluated symbolically to obtain ground truth and rendered into...
-
07
XCoT-VLA: Executable Chain-of-Thought for Vision-Language-Action Driving
Foundation Model Team, XPeng Inc
cs.AI
Vision-Language-Action (VLA) models can connect scene understanding, semantic reasoning, and trajectory generation for autonomous driving. However, verbose natural-language Chain-of-Thought (CoT) is poorly suited to real-time control because it is open-ended, costly to decode, and difficult to optimize as an action-facing representation. We propose XCoT-VLA, which replaces descriptive rationales with compact executable CoT tokens learned from...
-
08
FedCGR: Federated Cross-Domain Generative Recommendation
Zhuodong Liu, Hugen Lv, Xiangyu Li, Bohan Guo, Peiyu Hu
cs.AI
Cross-domain recommendation (CDR) transfers preference knowledge across related domains, but federated deployment makes cross-domain alignment difficult because the behavioral anchors that align item spaces, such as overlapping users and shared interaction signals, are often sparse, unavailable, or privacy-sensitive across clients. To address this tension, we revisit federated CDR as generation over a stable semantic item language. By...
-
09
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
Vaibhav Singh, Soumya Suvra Ghosal, Sarvesh Gharat, Soumyabrata Pal, Ramasuri Narayanam, Dinesh Manocha
cs.AI
Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies reveal that sequential test-time scaling often yields diminishing or even negative returns, as longer traces exhibit increased uncertainty, error compounding, and drift from the original problem. We propose ThinkRetrieve, a test-time scaling framework that augments the...
-
10
IO Factory: Simulating AI-Enabled Influence Campaigns at Scale
Lukasz Olejnik, Wenchao Dong, Jonas R. Kunst, Signe Riemer-Sørensen, Tobias Herb, Meeyoung Cha, Daniel Thilo Schroeder
cs.AI
We introduce IO Factory, an AI-driven framework for simulating information and influence campaigns as fully integrated, traceable processes. The threat of digital manipulation now extends beyond persuasive text from individual language models to AI swarms, i.e., persistent groups of coordinated agents that adapt to platform feedback and disguise organized campaigns as ordinary social interaction. Because such campaigns cannot be identified...
-
11
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI
Qianggang Ding, Xingyao Wang, Rui Feng, Zhibin Wang, Feixiang Wang, Kelong Mao, Hao Sun, Zhiyao Luo, Jiankai Tang,...
cs.AI
After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither explains whether the person forgot, is confused, has side effects, or deliberately refused, nor what support is appropriate. This reveals a structural gap in Agentic AI: Digital Agents primarily transform software states, while Embodied Agents transform physical states; neither makes a person's...
-
12
Enhanced Filtering Algorithms for the Euclidean Traveling Salesperson Problem and its variants in Constraint Logic Programming
Alessandro Bertagnon, Marco Gavanelli
cs.AI · cs.LO
The Traveling Salesperson Problem (TSP) is one of the best-known problems in computer science and arises in many engineering applications, such as smart vehicles and intelligent transportation systems. In the "Euclidean" case, each node is defined by its coordinates in the plane and distances are computed using the Euclidean metric. In the Constraint Programming (CP) literature, the Euclidean TSP is typically addressed by computing the full...
-
13
Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction
Serafim Batzoglou
cs.AI
First-order concept synthesis asks a system to infer one formula that classifies labeled objects consistently across several finite relational structures. Every candidate can be evaluated exactly, but quantified first-order formulas form a vast search space, and LLM outputs are often semantically promising without being fully correct. We introduce Hypothesis Frontier, a verifier-guided neurosymbolic framework that evaluates each LLM formula...
-
14
EvoMem: Memory-Augmented Evolution for Code Optimization
Viktor Volkov, Valentin Khrulkov, Andrey V. Galichin, Danil Sivtsov, Nikita Glazkov, Olga Volkova, Konstantin...
cs.AI · cs.NE
Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related tasks and domains. However, existing LLM-driven evolutionary frameworks largely discard such knowledge, repeatedly rediscovering similar ideas and limiting opportunities for cross-run and cross-task learning. We introduce EvoMem, a persistent memory architecture for...
-
15
ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation
Jiangjie Qiu, Yijun Li, Xiaonan Wang
cs.AI · cs.LG
Autonomous chemistry increasingly depends on environments in which agents can repeatedly act, observe, and adapt.Physical laboratories provide essential real-material evidence but are costly to repeat and difficult to use for tightly matched interventions, whereas most digital environments keep the underlying experimental world largely fixed. We introduce ChemWorld, a programmable chemical environment in which reusable process and observation...
-
16
SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
Zhou Liu, Ligang Huang, Zeli Su, Zewei Pan, Zhaoyang Han, Xing Chen, Yuanfeng Song, Wentao Zhang
cs.AI
Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress. Raw interaction traces preserve such information but are long and noisy to condition on, whereas text-only skills often omit the visual state that makes a procedure...
-
17
Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
Kaivalya Rawal, Daria Onitiu, Brent Mittelstadt, Sandra Wachter, Chris Russell
cs.AI · cs.LG · stat.ML
Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rule of Thumb'' (RoT) explanations, a new approach to XAI based upon a novel formulation that identifies the most relevant features for predicting the behaviour of an AI system, for a particular datapoint. We show how RoT is well-suited to enable XAI in: (a) zero-shot classification using large...
-
18
Compositional Benchmark Synthesis for Hierarchical Human Action Recognition
Farnaz Soleimani, Abdelghani Chibani, Yacine Amirat, Ghazaleh Khodabandelou
cs.AI · cs.CV
Recognizing human behavior across levels of abstraction, from atomic actions to long-horizon intentions, requires data annotated along a semantic hierarchy. Large corpora provide isolated, atomically labeled clips without temporal composition, whereas recorded composite-activity corpora offer shallow, domain-narrow, fixedhierarchies. A benchmark-generation and evaluation frameworkis proposed that synthesizes a four-level...
-
19
Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution
Xun Li, Yiying Yang, Pengtao Li, Xiao Yao, Suyu Liu, Xiaoyang Ye, Ziyu Lu, Yuan Yao, Yangning Li, Yinghui Li, Wenhao Jiang
cs.AI
Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the literature. Existing methods either treat papers as unstructured context or model scholarly evolution as isolated citation chains, overlooking interactions among research trajectories. We propose Tree-of-Ideas (ToI), a two-stage framework. EvoTrace reconstructs branching scholarly trajectories...
-
20
Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence
Haoyu Zhang, Zhipeng Li, Xiaoying Tang, Tianshu Yu, Yiwen Guo
cs.AI · cs.CL · cs.CV
Omni-modal dialogue models can understand multimodal inputs and synthesize spoken replies, yet their responses remain visually disembodied. We introduce \textbf{Ex-Omni-2D}, an omni-modal dialogue framework that generates a coordinated response comprising text, personalized speech, and reference-conditioned video. Given a multimodal query, reference image, and reference audio, the model predicts a structured \textit{Visual Thought Plan} (VTP)...
-
21
Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory
Aijun Yang, Qianxue Guo, Ziyi Huang, Yuxuan Chen, Shiyou Qian, Jian Cao
cs.AI
Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments. However, providing complete execution trajectories to the LLM causes unbounded context growth and introduces noise. Existing compression methods reduce context at the cost of important details and often replace erroneous facts without repairing downstream reasoning derived from them. To address this problem, we propose...
-
22
REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems
Zixing Chen, Xingyuan Liu, Jie Zhu, Huaixia Dou, Shuo Jiang, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang
cs.AI
Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interactions between the agent and its environment, causing the agent to violate safety policies during execution. Yet existing evaluations often reduce agent safety to a single attack success rate (ASR), collapsing exposure, execution, observation, and adjudication and potentially conflating actual...
-
23
FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs
Jiaxin Pan, Mojtaba Nayyeri, Osama Mohammed, Daniel Hernandez, Rongchuan Zhang, Cheng Cheng, Steffen Staab
cs.AI
Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timestamps to be reasoned about are already known at training time, restricting each model to a single graph and vocabulary. We propose FITTER, the first fully-inductive structural model for temporal knowledge graph link prediction that supports cross-domain transfer: the inference graph may contain...
-
24
VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus
Rohit Sinha, Kunal Tilaganji, Tanuja Ganu, Nagarajan Natarajan, Amit Sharma, Vineeth Balasubramanian
cs.AI · cs.CV · cs.GT
Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Existing approaches either require expensive labelled supervision with inconsistent cross-task performance or aggregate scores from multiple sources by simple aggregations, missing a key insight: when these scores disagree, that disagreement itself carries important...
-
25
Operationalising Relative Causal Knowledge: Backbone Identifiability from Private Reports on a Shared Outcome
Fabrizio Russo, Mark Somers
cs.AI
The Relativity of Causal Knowledge (RCK) explains how a network of agents with different structural causal models can exchange causal knowledge through a shared interventionally consistent abstraction, or backbone. We ask the prior identification question that this transport mechanism presupposes: when is that backbone determined by the agents' private causal knowledge? In the basic two-agent common-effect case, two private causes influence...
-
26
Decision-Aware Approximation of Belief Functions for Evidential Combinatorial Optimization
Sohaib Afifi
cs.AI · math.OC
Reducing the number of focal elements of a mass function is classically driven by an intrinsic distance, such as Jaccard or Jousselme, that keeps the approximation close to the original as a body of evidence. We consider instead the case where the mass function feeds a linear combinatorial optimisation problem with evidential costs. What should then be preserved is not the closeness of the two mass functions, but the quality of the decision...
-
27
Curate Before You Connect: Identity and Ontology Tagging in a Production Knowledge Graph
Vaibhav Dangaich, Kevin Lewis, Kundeshwar Pundalik
cs.AI
Extraction produces candidate entities and relationships; writing them into a graph is where identity is decided, and identity decisions are destructive in a way extraction errors are not. A wrong type can be corrected later, but two records merged under one identity cannot be separated once their properties have been combined, and the merge leaves no error behind. This paper describes the ingestion and ontology-tagging layer that turns a...
-
28
HexEval: An Evidence-Driven Hexagonal Framework for Multidimensional Scholar Assessment
Xiaokang Qu, Yiting Lin
cs.AI · cs.DL
Scholar assessment plays a fundamental role in faculty recruitment, funding allocation, academic promotion, and talent discovery. Existing scholar assessment methods predominantly rely on bibliometric indicators and reputation proxies, while recent large language model (LLM)-based approaches mainly focus on evaluating individual research papers rather than comprehensively assessing scholars. We argue that scholar assessment should be...
-
29
Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent
Fanqi Zhou, Qiaosheng Chen, Zixian Huang, Gong Cheng
cs.AI
Although existing instruction data selection methods have introduced various metrics, the inherent complexity of real-world datasets makes it impractical for any single metric to generalize across all scenarios. Developers are thus often forced to manually inspect data and craft heuristic rules for each new application---a tedious and error-prone process. In this paper, we propose a paradigm shift from manual configuration to automated...
-
30
DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation
Xiaotong Wang, Dazhen Deng
cs.AI
Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and natural-language goals, but evaluating their usefulness remains difficult. Dashboard generation is open-ended, and neither static appearance nor successful execution alone captures analytical support and interaction quality. We introduce DashArena, to our knowledge the first benchmark for...
-
31
Reinforcement Learning-Based Laser Cutting Machine Parameter Optimization
Khanh Quan Pham, Majid Kundroo, Geunwoo Ban, Seongho Bae, Taehong Kim
cs.AI
Achieving high accuracy in laser-based cutting of optical films requires careful tuning of parameters such as focal length and laser power beam, adjusted according to the specific properties of each film type. Trial-and-error based traditional methods are used to find the most suitable cutting parameters for various films, but they are slow and inaccurate. To address this issue, this paper presents the Reinforcement Learning for Laser Cutting...
-
32
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
Chenhao Dang, Siyuan Xiong, Conghui He, Weijia Li
cs.AI
Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually constrain a language model's behavior space for repeatable, high-quality task execution. However, because strong closed-source models entail high inference costs, current popular agent harnesses, such as Codex and OpenClaw, remain prohibitively expensive when...
-
33
Measuring Semantic Abstractness of SAE Features via Nonlocality
Chuqiao Lin, Shivaji Sondhi, Xiao-Liang Qi
cs.AI · cs.LG
Sparse autoencoders (SAEs) have helped uncover mechanistic explanations for LLM behaviours such as reasoning, jailbreaking etc., via understanding the corresponding task-relevant and causally effective features. To evaluate such mechanistic explanations, downstream studies must distinguish surface lexical features from genuinely high-level ones. However, neither an autointerp-based semantic description nor causal steering utility fully...
-
34
MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
Yiqi Wang, Zihao Yan, Jiaqi Zhang, Zhangkai Wu, Mingkai Zheng, Zequn Sun, Yanming Zhu, Taotao Cai
cs.AI · cs.MA
Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action. Because restrictions propagate through derivations, summaries can conceal private, poisoned, untrusted, or revoked sources, enabling unauthorized reads or unsafe actions. Existing approaches provide semantic retrieval, scoped access, or lineage tracking, but do not clearly separate...
-
35
RadFusion: Towards Threshold-Controllable Radiology Report Generation
Ying Jin, Noel C. F. Codella, John Corring, Mu Wei, Dinei Florencio, Eric Horvitz
cs.AI · cs.CL · cs.CV
Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-specificity trade-off of their diagnostic content. Such control is essential because clinical scenarios diverge: emergency triage prioritizes sensitivity to reduce missed findings, whereas confirmatory interpretation emphasizes specificity to...
-
36
MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graph
Jung Hwan Lee, Kyu Ho Lee, Gwang Hoon Yoo
cs.AI
As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that systematically improves them. Current approaches optimize agent systems without accumulating transferable knowledge, accumulate knowledge without compositional reasoning over it, and lack a mechanism for that knowledge to self-evolve through operational evidence. MEGA (Meta Evaluation-Grounded...
-
37
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents
Caili Yu, Yiqi Wang, Jiaqi Zhang, Yiqun Duan, Mingkai Zheng, Zhangkai Wu, Kaize Shi, Taotao Cai
cs.AI
Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, tool use, answers, and subsequent memory writes. Existing defenses mainly detect or delete suspicious memories, or revise the current response. Deleting the source leaves already propagated claims, actions, and derived memories active, whereas resetting the store or...
-
38
GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning
Xin Xiao, Jiang Zhong, Junnan Zhu, Yingchao Feng, Peijin Wang, Yidan Zhang, Kaiwen Wei
cs.AI · cs.MA
Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challenging because EO workflows are constrained by sensing semantics, product dependencies, spatial and temporal compatibility, and parameter requirements. Existing agents often search a broad operation space for each query, while recent self-evolving systems do not fully organize heterogeneous EO...
-
39
INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators
Rose Niousha, Minwoo Kang, Narges Norouzi
cs.AI · cs.CY
Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, where student simulation is increasingly used for various applications such as evaluating tutoring systems, this gap is especially pronounced. Two students may submit identical submissions for entirely different reasons. We present INTERNAL STUDENT DIALOGUE (INSIDE), a student modeling...
-
40
Predicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot Learning
Jongwon Park, Inhyo Lee, Junhyeong Lee, Seunghwa Ryu
cs.AI · cond-mat.mtrl-sci
Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of stable structures remains difficult because available datasets are often strongly imbalanced toward dominant SG classes. We refer to dominant SG classes as major SGs and underrepresented classes as minor SGs. We introduce Dynamic and Diversity-enhanced Few-shot Retrieval and Rule-Guided Inference for Space-Group Prediction (DyRIS), an...
-
41
Multi-Granular Rationale-Guided Molecular LLM for Property Prediction
Junwoo Park, Minyoung Shin, Cheol Soon Lee, Sujee Lee
cs.AI · cs.LG
Large language models (LLMs) are widely applied across chemical tasks, such as molecular property prediction, which underpins drug discovery. Molecular LLMs represent a molecule through several modalities, notably a 1D SMILES sequence or a 2D molecular graph. Both encode molecular information implicitly, so the contribution of individual substructures remains opaque. Retrieval and augmentation methods add context, but from external sources....
-
42
Evaluating Rational Contracting in Natural Language
Bhavyesh Sajja, Max Kleiman-Weiner, Roger Zimmermann, Tan Zhi-Xuan
cs.AI · cs.CL · cs.GT
The emergence of language-based AI agents promises to transform the scope of machine economic activity. Instead of just proposing bids or following hard-coded protocols, such agents can be used to negotiate and execute agreements in open-ended natural language. However, most evaluations of these abilities have focused on one-off exchanges or simple economic games, leaving open the rich space of time-extended, contingent, and incomplete...
-
43
RLMOpt: Adaptive Prompt Optimization via Recursive Language Models
Subhash Bangalore Satheesha, Nirvik Pande, Deepthi Duddempudi, Bharath Dandala
cs.AI
Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization procedure: the algorithm determines which candidates to explore and how the search progresses, while the language model generates or refines prompt proposals. We introduce RLMOpt, a prompt optimizer that makes the search policy itself language-model-driven through a recursive language model (RLM)....
-
44
Quantum Incremental Learning with Mixed State Prototypes
Yu Wu, Qianli Zhou, Xinyang Deng, Wen Jiang, Kang Hao Cheong, Witold Pedrycz
cs.AI · cs.LG
Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints. In the Noisy Intermediate-Scale Quantum (NISQ) era, although quantum neural networks offer advantages in feature mapping, hardware limitations restrict circuit width. Furthermore, traditional quantum classifiers are constrained by the number of orthogonal basis states, limiting...
-
45
Rationale-Guided Learning for Multimodal Emotion Recognition
Sujung Oh, Jung Uk Kim, Sangmin Lee
cs.AI
Multimodal emotion recognition in conversation (MERC) requires understanding complex interactions between verbal and non-verbal cues. However, most existing approaches fundamentally treat this as a direct input-output (multimodal cues-emotion labels) mapping problem, overlooking the causal reasoning that humans use when interpreting emotions. We propose rationale-guided learning (RGL), a novel framework that transforms MERC into a...
-
46
Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning
Yuhang Cao
cs.AI
Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world. For autoregressive models, tool use naturally fits the generation process: the model emits a tool call, waits for the result, and then continues generating. Diffusion language models (dLLMs), however, reason by repeatedly refining many parts of their output in parallel, making this...
-
47
Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
Cong Chi Nguyen, Trang Mai Xuan, Vu-Duc Ngo, Kim-Ngan Thi Nguyen, Trong-Nghia Nguyen, Thien Van Luong
cs.AI
Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the 'black-box' nature of these models, combined with the high dimensionality of multimodal cyber-physical data, poses significant interpretability challenges. Static visualization dashboards may struggle to present complex relationships among multimodal cyber-physical features in a form...
-
48
Recovering Wasted Compute in Autoresearch Agents
Au Kwok Chun, Abhigyan Acherjee, Amrutha Rao, Zaiqian Chen, Kazem Meidani, C. Bayan Bruss, Micah Goldblum
cs.AI · cs.LG
A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have inspired large industry investment, motivated by their potential to automate time-consuming human labor and customize machine learning solutions for specialized applications. In this paper, we study the modeling pipeline at the core of these autoresearch systems and identify common failure modes...
-
49
Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects
Xin Xu
cs.AI
Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts. A recent framework of Takemura, Inoue, and Nishino analyzes them through an automorphism group of value relabelings and asks, as its central open question, when rules pin concepts down. We first show that the framework's key definition, one shared permutation applied at every position, does not apply as stated to...
-
50
Threat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement Learning
Xincong Hu, Lei Ou, Maosen Li, Jingtao Zhang, Liguo Hou, Zongzhang Zhang
cs.AI
Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes. The long-tailed nature of real-world traffic situations makes dangerous and rare interactions difficult to encounter through conventional sampling, limiting the ability of RL policies to learn robust safety behaviors. Existing...
-
51
Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models
Jiahui Han, Yuhui Yao, Xin Wang, Jiafei Cao, Mingxuan Zhang, Danfeng Shan, Huiqi Deng, Guanchu Wang, Xia Hu
cs.AI · cs.RO
Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks. However, their adversarial robustness remains largely underexplored, and exploiting this weakness can lead to physical-world harm. Existing attacks on VLA models often rely on pixel-space perturbations or white-box access, resulting in noticeable artifacts and limited deployability in real-world robotic systems. In this...
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.