cs.AI · 2026-11-04 · No. 163
Artificial Intelligence, 2026-11-04.
38 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
38 entries-
01
Adversarial Speculative Reasoning Improves Long Horizon Agents
Hongyin Luo, Wei Fang, Lijie Yang, Owen Stepan, Daniel Suit, Jeff Krapf, Dana Wensberg, Jack O'Brien
cs.AI
Speculative decoding has been treated purely as a systems optimization that speeds up large language model decoding without changing the model behavior. Under this view, the growing effort to train better draft models has been focused solely on acceptance rate. We argue that this view does not hold true for long-horizon agent reasoning. Measuring frontier open-weight models on complex agentic tasks with different speculative decoding...
-
02
You don't need long context
Peter Belcak, Saurav Muralidharan, Jindong Jiang, Yonggan Fu, Wonmin Byeon, Hanrong Ye, Ryan Angilly, Ali...
cs.AI
Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that frontier language models sacrifice little to no task accuracy when maintaining short contexts. We further demonstrate that LLM performance does not collapse on long-horizon software engineering tasks even...
-
03
The Geometry of Ignorance: Detecting Suppressed Knowledge in LLMs through Activation Fragmentation
Adar Peleg, Dvir Alsheich, Tomer Ashuach, Avi Mendelson
cs.AI
Evaluating whether a large language model (LLM) genuinely knows a concept remains a fundamental problem, since behavioral metrics can be fooled by suppression: a model that refuses to answer may still harbor recoverable knowledge. The framework measures the geometric coherence of \textit{anon-vectors}, the differences in hidden states between a concept-specific query and its anonymized paraphrase, and shows that genuine knowledge forms a...
-
04
JHiMA-WebRL: A Joint Hierarchical Multi-Agent Reinforcement Learning Framework for Long-Horizon Web Tasks
Shanka Subhra Mondal, Jiayun Wang
cs.AI
Multimodal web agents have shown promising capabilities for interacting with websites through graphical user interfaces (GUIs), yet realistic web tasks often require long-horizon, multi-step planning that remains challenging for monolithic policies. Such agents must jointly infer high-level plans, navigate through intermediate states, track progress over extended interaction histories, and execute visually grounded actions. Although prior...
-
05
AgentAM: An AI Agent for Spatter- and Defect-Aware Process Optimization in Laser Powder Bed Fusion
Olabode T. Ajenifujah, Amir Barati Farimani
cs.AI
Predictive models for laser powder bed fusion (LPBF) are rarely used on the shop floor because querying them requires programming and model-specific knowledge. We present AgentAM, a large language model (LLM) agent that gives process engineers natural-language access to CFD-trained surrogates of spatter and melt pool geometry for SS316L through the Model Context Protocol (MCP). Polynomial surrogates trained on 279 single-track simulations...
-
06
Learning Behaviorally Relevant Dynamics in Multimodal Neural Recordings
Parastoo Azizeddin, Eray Erturk, Maryam M. Shanechi
cs.AI · cs.LG · cs.NE
Multimodal neural data can enable a more complete understanding of brain dynamics underlying behavior. Modalities such as spiking activity, local field potentials (LFPs), and behavior capture diverse spatiotemporal aspects of brain processes, yet prior neural-behavioral models that separate sources of variability rely on a single neural modality. By leveraging these complementary strengths, multimodal neural fusion can provide a unified, rich...
-
07
Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning
Xujia Wang, Yixuan Liu, Shaohan Huang, Furu Wei, Lei Hou, Bin Xu, Juanzi Li
cs.AI
Generating HTML from natural-language specifications is an important application of code large language models (LLMs). Despite producing renderable pages, current models often fail to ensure functionality and visual quality during actual interaction. Existing methods typically target task-specific webpage supervision, leaving demanding interactive artifact optimization underexplored. Using mini-games as a challenging testbed, we expose...
-
08
Creating Power Flexibility in Datacenters via Query Routing
Shivam Patel, Bingqing Chen, Jared Fernandez, Guannan Qu, Gauri Joshi
cs.AI
The growing energy requirements of large language model inference highlight the need for datacenters to support safe grid operation by providing power demand flexibility, while maintaining service for interactive workloads. This work investigates query routing as a mechanism to enable such capability by dynamically allocating queries across different language model instances without deferring requests. We develop a general analytical...
-
09
Meta$^2$: Precomputing Reusable Knowledge for Online Harness Evolution in Long-Horizon Agents
Lingzhi Yuan, Yiguang Cai, Weize Liu, Siqi Yang, Feijiang Han, Yongkyun Lee, Udari Madhushani Sehwag, Furong Huang
cs.AI
Harness optimization improves long-horizon agents by refining the prompts, tools, memory, and hooks around a frozen model. Offline methods can learn from completed trajectories, but deploy one shared harness that may overfit training tasks and cannot react to evidence revealed during a new run. Online evolution can adapt before, during, or after one run through an evolver, but may have to reason about every intervention from scratch or rely...
-
10
From Opinions to Commitments: Unstable Assignments and Silent Choices in AI-Mediated Proposals
Sachit Mahajan, Javier Argota S{á}nchez-Vaquerizo, Arthur Capozzi, Dirk Helbing
cs.AI · cs.HC
Large language models (LLMs) are increasingly being used to turn citizens' opinions into collective proposals. These proposals can make assignments: who should act, what must be done, how much one should spend and by when. However, if the assignments change when the same opinions are processed again, publishing a single proposal can hide alternatives that participants never get to see. We examined this issue in four LLM mediators (three...
-
11
From AutoResearch to Continual AutoResearch: Do Agents Learn Across Tasks?
Jeremy Qin, Ruizhi Deng, Mohamed Osama Ahmed, Frederick Tung, Leo Feng
cs.AI
Autoresearch has shown that agents can autonomously write code, run experiments, and iteratively improve machine learning solutions. Yet most evaluations start a new agent session from scratch for each new problem, making them costly and leaving unclear whether agents can retain and apply prior insights when adapting to new tasks. We introduce CONTINUAL AUTORESEARCH, an open-ended environment that compares persistent and reset instances of...
-
12
The Platonic Brain: Representational Convergence in EEG Foundation Models
Nicolas Waehner, Enzo Tagliazucchi, Jacobo Sitt, Demian Wassermann, Giovanni Franco Gabriel Marraffini, Trinidad Borrell
cs.AI
The Platonic Representation Hypothesis (PRH) predicts that artificial neural networks converge on shared representations as scale and performance increase. We test whether these predictions hold for representations of the human brain with EEG foundation models. Using EEG recordings from six participants watching a television series, together with aligned visual and language content, we tested whether EEG foundation-model representations...
-
13
LatentTriad: Pre-Action Risk Representations for Malicious Agent Skill Detection
Zhe Yu, Yi Liu, Ying Zhang, Simin Chen
cs.AI
Large language model agents are increasingly extended with reusable skills, but untrusted skill content can induce operations outside the user's task. Detecting this contextual risk requires more than suspicious-pattern matching, while dynamic analysis incurs the cost of skill execution. We find that hidden states formed during prefill contain readable information about task-operation consistency, including across held-out expression forms in...
-
14
ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme
Aboubaker Seddiq Benterki, Jüri Vain, Gert Kanter, Leelo Aino Jürgenstein
cs.AI · cs.SC
We introduce ALBI (Agent for Learning By Induction), a neuro-symbolic ILP framework that replaces the ASP-based hypothesis generator in the Learning from Failures (LFF) paradigm with a Large Language Model (LLM), while retaining SWI-Prolog as a formal verifier. ALBI implements an iterative generate-test-constrain loop: the LLM proposes candidate hypotheses from structured prompts; Prolog tests each candidate; and diagnostic feedback drives...
-
15
Artifact-to-Capability: Diagnosing Breaks in Capability Formation of Self-Evolving Agents in a Controlled Environment
Ziqian Ban, Haoxiang Yang, Yanfei Zhang, Shixin Liang, Haoran Yu, Xu Lin, Shaobin Zhao, Xuran Li, Zhiyi Cheng
cs.AI
Self-evolving agents write interaction experience into artifacts and reuse them in later tasks. Most work supports such methods with three proxy signals: artifacts accumulate, behavior changes once they are loaded, and metrics rise. We call this signal-based evaluation. What these signals are meant to indicate, however, has not been defined. To fill this gap, we define capability formation from artifacts as five sequentially dependent...
-
16
FourSight: Stable FP4 RL Post-Training via Sequence Filtering and Sparse Channel Compensation
Yining Wei, Tianyuan Wu, Gu Gong, Yuechen Tao, Yinghao Yu, Xiaowen Chu, Wei Wang
cs.AI · cs.LG
Reinforcement learning (RL) post-training increasingly targets low-bit deployment, with NVFP4 weight-and activation quantization (W4A4) becoming the state-of-the-practice format. However, integrating NVFP4 into RL degrades rollout quality and amplifies cross-engine training-inference mismatch (TIM), destabilizing training. We show that these failures are concentrated rather than uniform - severely mismatched tail tokens concentrate in a few...
-
17
Modelling lock-in of AI adoption through skill erosion
Renaud Lambiotte
cs.AI · physics.soc-ph
Generative AI can improve immediate performance but may erode the human skills required for future work. We study a model in which individuals tend to imitate successful peers, while their independent skills grow with practice and erode with reliance on AI. Because each agent's skill reflects their history, non-users and AI users develop different skill distributions, which we derive exactly. Skill erosion can produce bistability and...
-
18
ScamWorld: An Interactive Environment for Evaluating Web Agents Against Online Fraud
Yutao Wu, Xiao Liu, Ming Wen, Hanxun Huang, Jun Wang, Xingjun Ma
cs.AI
Web agents increasingly browse, shop, and manage accounts on behalf of their users. Prior work has shown that they can be misled by adversarial content, including prompt injections and deceptive interfaces. Beyond such attacks, agents operating on the open web also encounter online fraud designed to deceive humans, including fraudulent online stores, fake investment platforms, and advance-fee schemes. How web agents respond to such fraud...
-
19
Amortized Nonlinear Variable Selection with Prior-Data Fitted Networks
Jin Zhu, Junxian Zhu
cs.AI · stat.ME · stat.ML
Variable selection is an important task for interpreting potentially complex systems in fields such as biology, business, and sociology. The importance of variable selection has attracted considerable attention in statistics and machine learning. In this paper, we are mainly interested in model-agnostic variable selection for identifying variables that have general nonlinear dependence on the response. We propose MambaPFN, short for...
-
20
DGC-Net: Cross-Modal Dynamic Routing with Global-Guided Compensation in Multimodal Sentiment Analysis
Linan Zhu, Huaijing Wu, Xiao Han, Yuhao Wang
cs.AI · cs.MM
User-generated videos, including opinion vlogs and video reviews, provide a rich source of people's attitudes toward products, services, and social topics. Understanding the sentiment expressed by speakers is important for analyzing online opinions, as transcripts alone may not capture the attitude and intensity conveyed through vocal tone and facial expressions. Multimodal sentiment analysis (MSA) addresses this need by integrating textual,...
-
21
HTCE: Homeomorphism-inspired Topological Cross-Scene Experience Canonicalization and Reuse for Object Navigation
Xiaoran Xu, Yupeng Wu, Tianyu Xue, Xuanran Dong, Yifan Xu, Xiaoshan Yang, Changsheng Xu
cs.AI
As embodied agents perform object-goal navigation across residential environments, they accumulate successful experiences whose semantic structure recurs across scenes even when geometric trajectories do not. Reusing such experience is challenging because differences in region naming and observation granularity produce distinct graph representations of similar approaches, while meaningful differences in anchors, branches, and endpoints must...
-
22
Feeling of Knowing in Large Language Models
Zichuan Fu, Xian Wu, Jingtong Gao, Wenlin Zhang, Jiaxuan Li, Binhao Wang, Yimin Deng, Guojing Li, Xiaopeng Li,...
cs.AI · cs.CL · cs.LG
Post-training updates change what large language models (LLMs) can answer, but may leave their answerability judgments misaligned. We study this knowledge-judgment desynchronization through functional feeling of knowing (FoK), which supports selective generation, retrieval triggering, and model routing without implying subjective experience. We propose two trainable channels: a knowledge channel that changes answerability and a FoK channel...
-
23
Reconstructing Fraudulent Strategies in Online Payments via Interpretable Inverse Reinforcement Learning
Huilin He, Weiyu Han, Linbo Shao, Ruobing Zuo, Xiao Tan, Shuai Chen, Dawei Cheng
cs.AI
Payment fraud causes financial losses and undermines users' trust in web payment services. Although fraud detection is a critical defense for payment security, complex and diverse fraudulent behaviors can still evade detection. Generating fraud samples for data augmentation can broaden detectors' coverage of different fraud patterns. However, existing methods matching the distribution of transaction attributes alone do not ensure that...
-
24
The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models
Chenyu Yi, Jiawen Zong, Sami Hormi, Bingquan Shen, Xudong Jiang, Alex Chichung Kot
cs.AI
The proliferation of Large Vision Language Models (LVLMs), trained on vast and often sensitive datasets, raised concerns regarding data privacy and unauthorized usage. Unlearnable Examples (UEs), which subtly perturb training data to mislead the models, have emerged as a promising defense method. This paper presents the first exploration of UEs specifically on LVLMs, which poses unique challenges due to their inherent multimodal nature. We...
-
25
Think Less, Locally: Local Preference Learning for Reasoning Compression
Muyao Yuan, Liyan Xu, Weizhan Zhang, Muyan Jiao, Jiangnan Li, Jinchao Zhang, Jie Zhou
cs.AI · cs.CL
Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient information has been obtained. Existing reasoning compression methods primarily operate on reasoning trajectories, paying less attention to the local decision of whether further reasoning is necessary given the current state. We propose LoCo, a local...
-
26
AgenticFinBench: Benchmarking Financial Agents on Diverse Tasks from Real-World Requests
Shu Zhou, Ziyang He, Yuxin Rao, Yudong Fang, Jiali Qian, Dongyuan Chen, Juntao Zhang, Yong Hu
cs.AI
Financial agents are becoming an important class of real-world AI systems. Financial tasks vary widely in type and difficulty, and many are open-ended with no ground-truth answers. However, existing benchmarks neither capture this breadth and open-endedness nor separate grounding from correctness. To bridge this gap, we introduce $\textbf{AgenticFinBench}$, a benchmark of 230 real-world financial tasks spanning 8 categories, 2 languages, and...
-
27
RAHC: Rule-Augmented Hyper-Relational Knowledge Graph Completion for Materials Synthesis
Jiawei Sun, Sijia Xu, Zihan Chen, Zhengyi Yang
cs.AI
Scientific discovery depends on reusing experimental knowledge, yet records scattered across papers and repositories are often incomplete. In materials synthesis, recovering missing conditions requires reasoning about the target material and the observed context of a specific experiment. Hyper-relational knowledge graphs (HKGs) represent this context through qualifiers, but existing completion methods leave domain knowledge and experimental...
-
28
Where Is the Truth When AI Agents Disagree? Dependence-Aware Belief Propagation for Unsupervised Truth Discovery (Extended Version)
Laure Berti-Equille
cs.AI · cs.CL · cs.DB · stat.ML
LLM agents often give conflicting answers to the same question, and many deployed agents are variants of one base model, so their errors are correlated. We study truth discovery among such agents: inferring the true answer and each agent's reliability without labels. Classical truth-discovery and crowdsourcing estimators reward an agreeing bloc and can fall below majority vote. We propose BP-TD, which adds per-agent decorrelation weights to...
-
29
Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks
Andrew Semenov, Svyatoslav Dorofeev
cs.AI
Large language models are candidates for collecting and analyzing records in criminal investigations and mass surveillance. Their capability and accuracy in this work cannot currently be measured. Real deployments lack the ground truth needed to score a model's conclusions, and no benchmark evaluates these capabilities in a simulated environment. We present Kierston, a city-scale simulation engine, and KierstonBench, a benchmark that tests...
-
30
Reducing Logprob Without Causal Verification: Diagnosing SAE-Based PII Suppression in LLMs
Chaerin Lee, Wonho Lee, Sohee Park, Daeseon Choi
cs.AI
SAE-based feature-level interventions to suppress PII leakage in LLMs are primarily evaluated by log-probability reduction. We show that this criterion cannot distinguish feature specific suppression from a magnitude artifact: a direction-agnostic effect of sufficiently large activation perturbations. Across 36 (model, layer, PII type) cases, we compare selected SAE feature interventions with coherencematched random direction controls using...
-
31
TactiNavi: Serving and Revising an LLM Game Coach with Explicit Strategy Conditions
Qi Liu, Xiaoyang Yuan, Zhuomeng Zhang, Yubin Ruan, Xinyi Mou, Wenjin Wang, Hanying Jiao, Di Wu, Jinke Li, Jingxuan...
cs.AI
A deployed LLM coaching agent answers requests whose correct response depends on player state and game version, so advice that is right for one player can be wrong for the next. We describe TactiNavi, the serving system behind the LLM coach of a commercial open-world game, which makes strategy applicability an explicit artifact shared by offline compilation, online execution, failure diagnosis, and release. An offline compiler turns versioned...
-
32
When Should an LLM Steering Edit Depend on the Input?
Rachael Harkness, Konrad Rawlik
cs.AI
An activation steering edit should depend on the input exactly when the destination varies \emph{inside} the class a query requests, and that is measurable before any rule is fitted or applied. Contrastive Activation Addition (CAA) adds one fixed direction to every input, the difference of the class means. Conditioning it on the requested class accounts for the between-class variation in the required displacement and leaves the within-class...
-
33
SAT Encoding for Set of At-Most-K Cardinality Constraints with Ladder Shape
Hieu Truong Xuan, Tuyen Kieu Van, Khanh To Van
cs.AI
This paper presents a novel SAT encoding designed to represent a sequence of At-Most-K cardinality constraints arranged in a ladder-like structure, referred to as the Ladder AMK constraint. These AMK constraints feature a ladder-like arrangement, with shared common variables in the center and two variables differing at the beginning and the end. The proposed encoding first decomposes the sequence of AMK constraints into separated blocks, then...
-
34
ValQID: Learning the Net Value of Semantic Query Groups for Web Device Identification
Yifan Yang, Zhen Huang, Weijia Shi, Xichen Tan, Zhihuang Liu, Xionglve Li, Zhiping Cai
cs.AI
Web interfaces are widely used to access network services and manage networked devices. Identifying the vendors and types of devices behind Web interfaces is a critical step in asset inventory, security management, and risk assessment. Device identity cues are dispersed across page text, configuration fields, and management functions, and interpreting them often requires linking related Web objects. Responses and objects require different...
-
35
A research world model of power engineering learns its dynamics and reveals what-ifs
Fanping Sui, Ying Zhang, Liwei Lin
cs.AI · eess.SY
Decisions about the direction of research in power engineering determine which technologies mature and, through them, shape infrastructure that lasts decades, yet their consequences cannot be observed before they are taken, and existing forecasts of research fields extrapolate a single trajectory. Here we introduce research world models, which treat a research field as a dynamical system that can be acted upon, and establish one for power...
-
36
Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent Systems
Chandler Smith, Qi Guo, Cecilia Elena Tilli, Sophia Hatz, David Demitri Africa, Patricia Paskov, Christian Schroeder...
cs.AI · cs.MA
The deployment of AI agents in multi-agent settings enables inter-agent influence, whereby agents can strategically steer each other's behaviour towards an intended outcome. Such capabilities pose novel risks, as malicious agents could direct others towards harmful actions. In this work we investigate three such capabilities - persuasion, deception, and coercion - across five realistic evaluation environments and a variety of agents...
-
37
Are LLM Assistants Regulatory Ready? Answers from regenold's 2026 EU AI Act Q&A Challenge
Marco Virgolin, Thomas Haszprunar, Maximilian Regenold
cs.AI · cs.MA
Large language model (LLM) assistants are increasingly proposed for regulatory affairs, yet their reliability in regulatory tasks remains unclear. We introduce the EU AI Act Q&A Benchmark, an expert-curated benchmark of 110 open-ended questions about the EU AI Act (Regulation (EU) 2024/1689). Each question comes with an exemplary answer, question-specific correctness criteria, and expected references. Evaluation measures answer correctness,...
-
38
Learnings and Pitfalls from AI-Assisted A/B Experimentation at Scale
Brett Daley, Ilya Gorbachev, Anubhav Natani, Nicholas Brown, Athena Dai, Rachel Song, Marcin Pekalski, Josip...
cs.AI
A/B testing underpins product decisions by providing trustworthy, reproducible quantification of proposed changes' effects. Growing large language model (LLM) capabilities have motivated efforts to automate experimentation workflows. Yet LLMs are nondeterministic and prone to hallucination, properties that conflict with the trust experimentation systems must provide. Experiments are also operationally messy: diagnosing anomalies, debugging...
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.