cs.AI · 2026-11-07 · No. 166

Artificial Intelligence, 2026-11-07.

48 new papers in cs.AI. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

48 entries
  1. 01

    SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

    Qile Jiang, George Em Karniadakis

    cs.AI · cs.NE

    LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per...

    arxiv.org/abs/2611.08483 · PDF

  2. 02

    Scientist World: Grow a Research World for AI-Scientists

    Taiming Lu, Sachin Konan, Zhuang Liu

    cs.AI · cs.CL · cs.LG

    AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted $-$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes an executable environment. Our autonomous pipeline extracts each paper's open-ended research question and reproduces its...

    arxiv.org/abs/2611.08478 · PDF

  3. 03

    ReproBridge: Building Reproducibility into ML Research Artifacts

    Yubo Wang, Rui Meng, Jaehyun Nam, Tomas Pfister, Jinsung Yoon

    cs.AI

    Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask whether preserving recovered procedures and decisions improves subsequent independent reproduction. We define a standardized...

    arxiv.org/abs/2611.08452 · PDF

  4. 04

    The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI

    Julian Kunkel, Ali Doosthosseini

    cs.AI

    Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation. Yet the model sees the current dialogue but not the workspace around it. We explore meta access---giving the assistant a structured, permissioned view of the interface itself and propose a ladder of levels: feature tutoring; metadata, settings, and preference access; retrieval over summaries and...

    arxiv.org/abs/2611.08428 · PDF

  5. 05

    Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks

    E. Kelly Buchanan, Crystal Zhou, Scott W. Linderman, Christopher Ré

    cs.AI

    Coding agents are among the most economically consequential deployments of LLMs to date, making reliable evaluation increasingly important. Yet even benchmarks that are carefully validated at release can become stale. As models improve, they can discover valid solutions that existing verifiers reject, while changes to evaluation infrastructure can invalidate assumptions embedded in tasks and tests. We call the resulting accumulation of...

    arxiv.org/abs/2611.08417 · PDF

  6. 06

    The Gold Rush in AI4Math, II: What are signatures of AI-assisted Proofs?

    Yuanchuan Guo, Jiashun Jin, Zheng Tracy Ke, Bingcheng Sui

    cs.AI · stat.AP

    The growing use of AI in mathematics raises a question: can we detect AI involvement in proofs, separately from AI assistance with writing? Historical arXiv papers, recent papers disclosing substantive AI use, and manuscripts released by OpenAI provide a rich empirical basis for studying this question. However, several challenges remain: lack of matched case-control pairs; potential incompleteness of disclosure; and lack of ready-to-use...

    arxiv.org/abs/2611.08412 · PDF

  7. 07

    StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning

    Yang Ouyang, Jung-Eun Kim

    cs.AI · cs.CL · cs.LG

    Self-consistency (SC) is a widely used decoding strategy for improving chain-of-thought reasoning, but it requires sampling many complete reasoning trajectories with a preset budget. Its efficient variants reduce the cost mainly by stopping full-trajectory sampling early or distributing the number of samples across questions. In this paper, we propose StepBack, a step-level error-localized resampling method for efficient test-time reasoning....

    arxiv.org/abs/2611.08403 · PDF

  8. 08

    Learning a patient world model for health system simulation in intensive care

    Yingtai Li, Ruoyan Wang, Yu Li, Shaohua Kevin Zhou

    cs.AI

    Designing healthcare strategies requires anticipating their clinical and operational consequences before implementation, a task that often relies on health system simulation. Such a simulation necessitates modeling how patient states evolve and generate care demands. However, conventional approaches typically tailor compact state transitions to a single policy question and omit history-dependent dynamics, thus requiring the redefinition of...

    arxiv.org/abs/2611.08392 · PDF

  9. 09

    NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma

    Pengkai Wang, Wei-Wei Zhang, Yan Li, Min Tang, Zhitian Hou, Zeyu Liu, Guanghao Zhu, Yuanyi Wang, Yanggan Gu, Wenjun...

    cs.AI

    Current medical benchmarks typically break down clinical competence into isolated factual questions, single-image tasks, or static case vignettes. These tests score individual answers, but reveal less about whether a model can integrate subspecialty knowledge with multimodal evidence and track a patient's condition throughout a course of care. To close this gap, we introduce NPCBench, a clinical apprenticeship benchmark for nasopharyngeal...

    arxiv.org/abs/2611.08369 · PDF

  10. 10

    Enhancing Local and Global Structure in Compressed AI Agent Memory

    Henry Han

    cs.AI

    AI agents store text as embedding vectors and compress them at scale. A compression is accepted when each item's nearest neighbors survive, but agents also consolidate, delete, and compare memories, tasks that depend on which items lie far apart. We evaluate both ends with two label-free fidelities from our prior work: the local fidelity $L$ at 10 neighbors and the global fidelity $G$ at 30 to 50 percent of the memory. At 96 bytes per...

    arxiv.org/abs/2611.08341 · PDF

  11. 11

    Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement

    Wenbo Huang, Jianxin Bi, Shunyu Yang, Ruiyang Si, Rui Ni, Qiang Wang, Shulong Jiang, Yintianrun Zhang, Feixiang...

    cs.AI · cs.RO

    Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks. Several recent works expose the benchmark's success criteria to the learning agent, a practice we call Criteria Exposure (CE). These criteria, originally written to verify policies trained by imitation learning, often demand more than the corresponding language instructions, so a score from such a verifier may not faithfully reflect...

    arxiv.org/abs/2611.08318 · PDF

  12. 12

    Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation

    Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh Jeirani

    cs.AI · cs.CL · cs.LG

    Large language models (LLMs) are increasingly used in biomedical and cognitive neuroscience, but their ability to reason reliably over heterogeneous knowledge graphs (KGs) remains unclear. We benchmark five LLMs (GPT-5.1, Gemini 2.0 Pro, Llama 3, Qwen, and BioGPT) across five KGs: DrugBank, NeuroSynth, Cognitive Atlas, Brain Map, and GDPKG. We introduce a multitier query dataset to evaluate reasoning depth and factual accuracy under KG-aware...

    arxiv.org/abs/2611.08315 · PDF

  13. 13

    RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines

    Roko Parac, Christos Ziakas, Leo Ardon, Alessandra Russo

    cs.AI · cs.LG

    Reward machines (RMs) have been proposed as a reward formulation in reinforcement learning (RL) to capture non-Markovian tasks where credit assignment depends on history. By representing reward functions as automata, RMs expose the task's temporal structure and allow such rewards to be handled within a Markovian framework. However, they assume a labelling function, a proposition-grounding oracle for observations, which must be manually...

    arxiv.org/abs/2611.08308 · PDF

  14. 14

    First-Token Attraction in Mamba Dynamics

    Trinh T. Nguyen, Minh-Khoi Nguyen-Nhat, Duy-Tung Pham, Hoang-Son Do, Tan Minh Nguyen, Thieu N. Vo

    cs.AI

    We study token dynamics in deep Mamba models, with a particular focus on the attracting role of the first token. Unlike attention mechanisms, where token interactions are governed by positive scalar coefficients, Mamba dynamics involve full matrix-valued interaction coefficients with no positivity or definiteness guarantees. This structural difference makes Mamba dynamics substantially harder to analyze and prevents the direct application of...

    arxiv.org/abs/2611.08303 · PDF

  15. 15

    A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing

    Omer Ebead, Claude Formanek, Joel Z. Leibo

    cs.AI

    Contextual integrity (CI) holds that appropriate information flow depends on context-specific norms. The same disclosure may be appropriate in one context and inappropriate in another. We build a generative model of contextual integrity to study information sharing through simulated conversations. Two actors played by large language models exchange messages, with one holding private information and the other seeking it. We examine how sharing...

    arxiv.org/abs/2611.08284 · PDF

  16. 16

    LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation

    Hang Zhang, Qihao Ye, Litong Liu, Yunbei Zhang, Yugyung Lee, Yue Zhou, Bowen Liu, Emily First, Cheng Han, Qiao Zhuang

    cs.AI

    Neural theorem proving increasingly uses retrieved premises and project context to support proof generation. Evaluating these resources requires measuring the advantage of target-selected declarations over comparable alternatives and how this advantage depends on training. We introduce LeanContext, a benchmark of 129,826 Lean whole-proof generation problems, to investigate these questions. We group selected complete preceding mathematical...

    arxiv.org/abs/2611.08277 · PDF

  17. 17

    The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model

    Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe, Claus Metzner, Helmut Grabner, Patrick Krauss, Achim Schilling

    cs.AI · cs.CL · cs.CV

    Multimodal language models can simulate different observers, yet it remains unclear how assigned perspectives reshape their internal representations and whether these changes govern their judgements. Here, we investigate the representational geometry of persona-conditioned visual interestingness in Qwen3-VL-8B-Instruct. Across 100 images and 53 prompting conditions, we systematically vary persona content and the linguistic framing used to...

    arxiv.org/abs/2611.08262 · PDF

  18. 18

    Value-oriented policy distillation for interpretable wind farm power control

    Max Bruninx, Timothy Verstraeten, Jan Decuyper, Ann Nowé, Jan Helsen

    cs.AI · eess.SY

    Wind farm power control can help the system maintain balance and avoid blackouts. In Europe, this can be achieved through implicit balancing, where a wind farm adjusts its power setpoint in anticipation of the imbalance price using information published by the Transmission System Operator. Thereby, the wind farm helps restore system balance while also reducing its own imbalance costs resulting from forecast errors. However, implicit balancing...

    arxiv.org/abs/2611.08245 · PDF

  19. 19

    Signals, Evidence, and Context: User Scrutiny in Real-World LLM Conversations

    Ahana Biswas, Yu-Ru Lin

    cs.AI

    Large language models (LLMs) often present synthesized answers without making their supporting evidence easy to inspect. We study how features of these answers relate to users' subsequent accepting, checking, and challenging in 489,283 assistant-user response pairs from ShareChat and WildChat. Broad attribution language appears in 31.9% of qualifying responses, compared with explicit URLs in 1.33%, revealing a gap between claims of grounding...

    arxiv.org/abs/2611.08232 · PDF

  20. 20

    SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving

    Sai Vallurupalli, Francis Ferraro

    cs.AI · cs.CL

    Complex problems with limited context, such as claims, require a means to obtain additional knowledge necessary for solution reasoning. We propose a multi-agent framework, SMART, to obtain knowledge through capturing the implicit state of participating entities in a problem context. SMART curates the state knowledge as diverse, complementary and solution-salient premises using a variety of LLMs and a structured role-based prompt strategy....

    arxiv.org/abs/2611.08196 · PDF

  21. 21

    BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone

    Doojin Baek, Junyeob Baek, Mingyu Jo, Hosung Lee, Taegu Kang, Gyubin Lee, Sungjin Ahn

    cs.AI

    How would we know whether a machine truly understands the world? We argue that one key capability is \textit{observational theory learning}: acquiring reusable theories from pure observations and applying them to new situations. Current visual reasoning benchmarks focus primarily on the latter, presenting each task as a few-shot puzzle grouped by a common rule. We introduce BabyTheorist, a benchmark for controlled training and evaluation of...

    arxiv.org/abs/2611.08177 · PDF

  22. 22

    PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?

    Yue Zhang, Jilei Sun, Liqiang Jing, Yijie Wei, Ruohan Yang

    cs.AI

    Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal PCB routing agent inspired by how human engineers coordinate global strategy with local execution. A Global Routing Planner combines...

    arxiv.org/abs/2611.08175 · PDF

  23. 23

    A Generative Foundation Model for Multimodal Tokamak Tasks

    Yingshuai Ji, Haodong Feng, Guohong Deng, Gelin Bian, Yue Wang

    cs.AI · cs.CE

    Tokamak experiments record diverse measurements, including waveforms, profiles, fields, and scalars, which are used to reconstruct the plasma, forecast its evolution, recover associated control signals, and estimate disruption risk. Most models are built separately for one task and a fixed set of inputs and outputs, and each relies on a prescribed subset of diagnostics rather than structuring the full multimodal observation set to extract...

    arxiv.org/abs/2611.08153 · PDF

  24. 24

    Create Your Own Work Stack: Deploying Self-hosted AI and Tooling in a Tech Startup

    Saad Ahmed Bazaz, Talha Amjad, Abdurrehman Subhani, Sohaib Ahmed Bazaz, Abdullah Aamir

    cs.AI

    Self-hosting AI is often presented as a way to reduce inference costs and increase control, but deployment introduces its own costs. We report our experience deploying a hybrid AI stack at Grayhat Developers, a small software company with an AI-intensive development workflow. Our initial motivation was to counter the growing cost of commercial AI usage: Claude/Codex incurred approximately \$325 per month, with more than 25.93 billion recorded...

    arxiv.org/abs/2611.08116 · PDF

  25. 25

    MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation

    Kangjie Zheng, Amirhossein Vahidi, Liying Jin, Joseph Clarke, Vijaya Baskar MS, Connor Rogerson, Mengji Zhang,...

    cs.AI · q-bio.GN

    Modeling gene regulation in single cells requires jointly representing DNA sequence, chromatin accessibility, and gene expression across regulatory scales. Sequence-based models capture DNA-level regulatory grammar but often lack cell-level resolution, whereas many single-cell omics models represent genes and peaks as fixed-vocabulary tokens without their underlying sequence. Here, we present MUSS, a sequence-based multi-scale model for...

    arxiv.org/abs/2611.08086 · PDF

  26. 26

    DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels

    Jinho Park, Se Young Chun, Mingoo Seok

    cs.AI · cs.LG

    Efficient deployment of large language models (LLMs) on mobile devices requires balancing performance with compute and memory constraints. Post-training compression is an effective approach to managing this trade-off, while requiring much less computation than in-training counterparts. We propose DictLLM, a dictionary-based compression scheme in which weight matrices within grouped layers are decomposed into a shared dictionary and...

    arxiv.org/abs/2611.08082 · PDF

  27. 27

    When Imperfect Automated Fact-Checking Backfires: Social Learning in the Presence of Misinformation

    Zixuan Liu, Ming Cao

    cs.AI · eess.SY

    Automated fact-checking tools, cheap and fast but imperfect, are increasingly available on social platforms. We study when such tools can backfire in a sequential social learning model of misinformation. Agents observe an article's reliability and their predecessors' actions, which indicate whether they liked or disliked the article. They may also pay to fact-check it. We examine how welfare, defined as the probability of a correct cascade,...

    arxiv.org/abs/2611.08053 · PDF

  28. 28

    Secure Formal Raising: Protecting the Development of AI through Executable Properties

    Rolf Drechsler, Christina Plump

    cs.AI

    Model raising revisits Turing's developmental view of machine intelligence. Formal Raising (FR) has recently been proposed to complement this view with explicit behavioral properties. This paper extends that proposal to the security of the raising environment. Secure Formal Raising (SFR) models policy integrity, authorization, and confidential data flow using four-valued evidence that preserves unknown and inconsistent assessments. We prove...

    arxiv.org/abs/2611.08042 · PDF

  29. 29

    TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research

    Yifan Luo, Zhengying Liu, Yang Yuan, Zhilin Yang, Andrew Chi-Chih Yao

    cs.AI · cs.CL

    Can large language models (LLMs) advance theoretical computer science and resolve its long-standing open conjectures? To study progress toward this goal, we introduce TCSExam, a unified framework and benchmark covering the full range of TCS research. It evaluates theorem proving, solver engineering, and constructions alongside direct attempts to resolve open conjectures, capturing both concrete research accomplishments and progress toward...

    arxiv.org/abs/2611.07962 · PDF

  30. 30

    A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems

    Yao Huang, Yichi Zhang, Yifan Wang, Yitong Sun, Haoyu Dong, Jifan Ma, Jinzhe Tu, Xiaojian Li, Sören Mindermann, Wei...

    cs.AI · cs.CL · cs.LG

    Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with diminishing human oversight, raising the risk of loss of control: systems acting beyond effective human control with potentially irreversible consequences. Because such failures may become observable only after containment is difficult, they must be assessed prospectively. We introduce a behavioural framework that decomposes loss-of-control risk...

    arxiv.org/abs/2611.07953 · PDF

  31. 31

    Circe: Training-Free LLM Self-Evaluation via Component Interaction Consistency

    Shuyi Miao, Zheng Li, Xu Xie, Linrui Xu, Fei Shen, Xiaoyu Du, Tat-Seng Chua

    cs.AI

    As large language models (LLMs) are increasingly deployed in real-world applications, evaluating the correctness of their responses is crucial for reliable use. However, such evaluation is challenging because reference answers are rarely available in practice. Existing reference-free methods mainly rely on output signals, which may assign high scores to incorrect responses and thus do not necessarily reflect correctness. This motivates...

    arxiv.org/abs/2611.07948 · PDF

  32. 32

    ChemE-as-Code: An Open-Source Platform for Agentic AI in Chemical Engineering

    Artur M. Schweidtmann

    cs.AI

    ChemE-as-Code provides an open-source environment in which AI agents built on large language models (LLMs) can carry out chemical engineering work and engineers can check it. Its calculation tools range from catalysis through process simulation to plant layout, HAZOP and life cycle assessment, and skills tell a general-purpose agent how to use them. Engineering files are linked, machine-readable and versioned in Git; calculations run outside...

    arxiv.org/abs/2611.07947 · PDF

  33. 33

    How Finite Brains Generalize Without Bound: Spatial Memory as a Universal Computer

    Yuhang He, Si Wu

    cs.AI

    A child who learns to add small numbers adds numbers of any length. LSTMs and Transformers trained on short sequences fail on longer ones. We trace the difference to what a learner reads when it decides. A position, a count or a time keeps taking new values as the input grows: it is a coordinate, and a learner that reads one meets in every long input values its experience never covered. Whether two things are the same has the same two answers...

    arxiv.org/abs/2611.07920 · PDF

  34. 34

    Adaptive Semantic Branching: Disagreement-Localized Cross-Trajectory Regeneration for Reasoning Candidate Expansion

    Jeong-Yoon Kim, Tae-Yoon Lee

    cs.AI

    Reasoning trajectories generated for the same problem often arrive at conflicting answers. These disagreements reveal alternative intermediate decisions that can be reused to explore new solutions. We introduce Adaptive Semantic Branching (ASB), a training-free inference procedure that turns cross-trajectory disagreement into targeted candidate generation. ASB first groups independently sampled trajectories by extracted final answer, selects...

    arxiv.org/abs/2611.07918 · PDF

  35. 35

    GuidedWAM: Training-Free Energy Guidance for World Action Models in Autonomous Driving

    Xiyan Su, Finn Rasmus Schäfer, Hojun Lim, Frank Diermeyer, Johannes Betz, Markus Lienkamp

    cs.AI · cs.RO

    World action models (WAMs) for autonomous driving couple the driving policy and the visual world model in a single generative network whose objectives are fixed post-training. Conditioning on a new driving objective requires retraining. We study energy guidance as a general mechanism and present GuidedWAM, a model-agnostic framework for injecting driving objectives into frozen WAMs at sampling time. Our framework constructs each objective as...

    arxiv.org/abs/2611.07912 · PDF

  36. 36

    Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency

    Karthik Ravula, Sathwik Kowtha, Rishabh Verma, Kala Mehak Jain, Gunjit Mittal

    cs.AI · cs.CL · cs.IR

    Conversational agents can retrieve information directly or delegate retrieval to a subagent. This design choice affects how retrieval history is maintained, what context each model call receives, and what information must be re-retrieved in follow-up questions. We compare three designs: skill-based retrieval in the main agent, a non-persistent retrieval subagent that generates a findings response, and our persistent retrieval subagent, which...

    arxiv.org/abs/2611.07899 · PDF

  37. 37

    When Bigger Becomes Brittle: Why Compression Hurts More as Language Models Scale

    Gautam Gupta, Dikshant Kukreja, Unique Kumar, Avni Mittal, Deepanshu Dabas, Kshitij Sah, Erik Cambria, Rajiv Ratn...

    cs.AI

    Quantization and pruning reduce the cost of deploying language models, but their effects are usually reported as benchmark scores. Such scores record only the loss that remains at the output. Inside the model, compression damages some components more than others, and the rest of the network can partly compensate. The observed loss therefore reflects both the damage and this compensation, which benchmark scores cannot separate. How the two...

    arxiv.org/abs/2611.07891 · PDF

  38. 38

    Responsible GenAI Use During Active Armed Conflict: Evidence from Sudan's Emergency Response Rooms

    Dalia Ali, Yearin Lee, Cheng Yu, Ro Encarnación, Alsanosi Adam, Danaé Metaxa, Ingmar Weber, Orestis Papakyriakopoulos

    cs.AI · cs.HC

    Armed conflict can increase the value of Generative AI (GenAI) while undermining the conditions required for its responsible use. Yet the perspectives of community-based humanitarian responders working under these conditions remain underrepresented in responsible AI research. We examine GenAI use in Sudan's Emergency Response Rooms (ERRs), a community-led humanitarian network, through an exploratory survey of 89 respondents and 15...

    arxiv.org/abs/2611.07874 · PDF

  39. 39

    FARR: Forecast-Aware Residual Refinement with Matched Endpoint Evidence for Long-Horizon Time-Series Forecasting

    Yiyang Zhang, Yuli Zheng, Bin Li, Meimei Zhang, Qiang Sun

    cs.AI

    Large language models use auxiliary conditioning to incorporate additional information into time-series forecasts. However, auxiliary conditioning does not consistently improve accuracy and can increase forecasting error when its influence is poorly matched to the observed temporal context. We propose Forecast-Aware Residual Refinement (FARR), which learns to correct forecasts using endpoint evidence. FARR obtains a valid forecast under the...

    arxiv.org/abs/2611.07870 · PDF

  40. 40

    Generate-then-Rank: Learning Symbolic Goal Interpretation for Embodied Agents

    Jisen Lei, Huizhi Liang

    cs.AI · cs.CL · cs.RO

    Goal interpretation is to translate a natural language instruction into a formal symbolic goal that a planner can execute. It is critical for embodied agents because any error here propagates to every downstream planning and action step. Doing it well requires both generating suitable candidates and reliably selecting among them. We present a two-stage generate-then-rank approach to Goal Interpretation in the Embodied Agent Interface (EAI)....

    arxiv.org/abs/2611.07825 · PDF

  41. 41

    The Intrusion Pathway: How Non-Evidential Context Degrades Language Model Performance

    Dikshant Kukreja, Gautam Gupta, Avni Mittal, Avinash Anand, Kritarth Prasad, Zhengkui Wang, Timothy Liu, Rajiv Ratn...

    cs.AI

    Language models lose accuracy when a prompt contains non-evidential context: irrelevant statements from unrelated domains, or random off-distribution tokens, with no competing answer and no semantic overlap with the query. Such noise pervades retrieval-augmented, tool-using, and long-context deployments, yet the failure has lacked a mechanistic account. We trace the corruption to the Intrusion Pathway, which starts with MLPs enriching both...

    arxiv.org/abs/2611.07778 · PDF

  42. 42

    RIVER: Evidence-guided multi-agent retrieval for enzyme--reaction discovery

    Yifan Chang, Yunze Li, Feifei Jiang, Juntao Wu, Xin Chen, Han Hu, Yucheng Wu, Wei Tang, Mingqian Ma, Wanli Ouyang,...

    cs.AI

    Enzyme function annotation and the identification of candidate enzymes for a given reaction are essential steps in connecting genomic information to biochemical reaction networks. However, existing methods rely on sequence or structural similarity or on training with known enzyme--reaction pairs, making it difficult to integrate biochemical evidence across large candidate spaces; they also struggle with retrieval tasks involving enzyme...

    arxiv.org/abs/2611.07757 · PDF

  43. 43

    Pediatric ECG foundation model via adult-to-pediatric fine-tuning: downstream tasks and clinical evaluation

    Yu Cao, Haiyan Xu, Xiaohan Li, Jian Yang, Yuqing Feng, Wei Wang, Haomin Li

    cs.AI

    Pediatric electrocardiogram (ECG) interpretation is complicated by age-dependent electrophysiological changes that limit direct transfer of adult AI models. We asked whether an adult ECG foundation model could be adapted to pediatric ECGs. Using 339,563 12-lead ECGs from 238,189 children, we compared direct application, pediatric fine-tuning, and training from scratch under an identical architecture. Direct transfer was poor (mean AUC...

    arxiv.org/abs/2611.07717 · PDF

  44. 44

    Towards Generalist Graph-Level Anomaly Detection

    Junjun Pan, Yixin Liu, Yu Zheng, Fuyi Li, Alan Wee-Chung Liew, Shirui Pan

    cs.AI

    Graph-level anomaly detection (GLAD) aims to identify graphs that deviate significantly from the majority. While recent advances have achieved competitive performance, existing approaches mainly follow a dataset-specific paradigm, requiring substantial in-domain data and training cost when applied to new application scenarios. This limits their scalability and practicality in real-world applications where labeled data is scarce and diverse...

    arxiv.org/abs/2611.07706 · PDF

  45. 45

    MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents

    Yizhen Jiang, Haowei Guo, Tianyi Bai, Zengjie Hu, Lu Ma, Zhengyang Zhao, Haoze Sun, Peng Pei, Wentao Zhang

    cs.AI

    Large language model agents are increasingly deployed through the Model Context Protocol (MCP), which allows them to discover and invoke tools across multiple servers at runtime. Existing MCP benchmarks primarily measure task completion; where they diagnose failures, they do so after execution rather than building specific reasoning, execution, and memory failure risks into task construction. We introduce MCPHallu, a benchmark for diagnosing...

    arxiv.org/abs/2611.07689 · PDF

  46. 46

    Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies

    Mete Erdogan, Mirac Suzgun, Aneesh Pappu, Guowei Xu, Batu El, Andrew A. Schoen, Furong Huang, John P. Dickerson,...

    cs.AI

    The performance of multi-agent LLM systems depends not only on the capabilities of the underlying models but also on information-sharing policies, which govern what information each agent observes and at what level of detail. But does providing AI agents with more detailed information always improve collective outcomes, or can transparency paradoxically degrade efficiency? To investigate this, we introduce empirical information design, an...

    arxiv.org/abs/2611.07667 · PDF

  47. 47

    PharmAgents2: Towards Autonomous End-to-End Drug Discovery

    Haichuan Tan, Bowen Gao, Tao Huang, Jiaxin Tan, Xin Hong, Baoguo Yao, Yifei Wang, Zhichao Deng, Hanji Du, Dapeng...

    cs.AI · q-bio.QM

    Drug discovery requires continuous scientific decision-making across a vast research space. We introduce PharmAgents2, an autonomous system for end-to-end drug discovery that combines knowledge-enhanced decision-making with organized large-scale exploration. Paper2Skill extracts transferable scientific decision knowledge from public sources and, together with expert-developed skills, supports research decisions. Self-Scaling Discovery expands...

    arxiv.org/abs/2611.07653 · PDF

  48. 48

    Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems

    Vladimiros Peilivanidis

    cs.AI · cs.SE

    Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write code, guess API payloads, and memorize operational constraints through prompt engineering. In practice, this burns massive context windows, inflates API bills, and produces brittle agents that fail unpredictably in production. In this work, we present Skillware, an open architectural framework and capability registry that formally...

    arxiv.org/abs/2611.07652 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.