cs.AI · 2026-10-20 · No. 149
Artificial Intelligence, 2026-10-20.
60 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
60 entries-
01
Train An Imaginative Agent
Jiaxin Ge, Junyi Zhang, Tianning Chai, Hanjun Yoo, Chenyang Wang, Xiuyu Li, Weijia Shi, XuDong Wang, Sewon Min, Luke...
cs.AI
A seemingly reasonable push in Sokoban can make the puzzle unsolvable. To avoid such mistakes, an agent has to anticipate the consequences of its actions before execution, especially when feedback from the real environment is sparse or actions are irreversible. We introduce Agentic Imagination (Agima), a training framework that trains an agent to imagine before acting, i.e. to be imaginative. Agima trains a single omni model to propose...
-
02
AnyGoal: On World Model Generalization Beyond Expert Rollouts
Heejeong Nam, Divyat Mahajan, Quentin Le Lidec, Randall Balestriero, David Klindt
cs.AI
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the learned dynamics must behave well beyond the specific state-action combinations observed in expert rollouts. Despite this, the relationship between data coverage, dynamics generalization, and downstream...
-
03
Same Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy
Ke Zhang, Sahchit Chundur, Jerry Peprah Owusu, Mohammad Javad Abdolhosseini Qomi, Maziar Raissi
cs.AI
LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool outputs out of the context window, saving them to files that the agent searches or reads on demand. We ask where this costs accuracy with a real scientific tool: PHREEQC, a widely used geochemistry simulator from the USGS, whose reports reach 846.8k characters and whose determinism lets every printed value be traced. Agents use it to...
-
04
ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry
Matt Turk, Brandon L. Neel, Diana M. Lopez, Zachary D. Smith, Grace N. Johnecheck, James B. Golden
cs.AI · cs.LG · q-bio.BM
Frontier agents retrieve structural metadata well and compute geometry from coordinates less reliably. We ask how much of a benchmark score reflects that gap and how much reflects the evaluation configuration around the model. We study ProteinGeoBench, a suite of 131 protein-structure tasks, using 4,249 rollouts from four frontier models and 4,486 further trials across 26 models. Three of the four frontier models fall within 0.031 of one...
-
05
Agent World Model in the Wild: Computer-Use Agent Environment Synthesis
Zhaoyang Wang, Qianhui Wu, Haorui Wang, Simon Yu, Baolin Peng, Canwen Xu, Hao Cheng, Wenlin Yao, Boyi Liu, Yite...
cs.AI · cs.CL · cs.LG
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce substantial security risks. We therefore propose Agent World Model in the Wild (WildAWM), a scalable pipeline for synthesizing controllable environments and tasks for training general computer-use agents (CUAs). Whereas existing...
-
06
SOMA: Continuous Monitoring and Intervention for System Two Reasoning with System One Models
Ruizhi Qian, Lei Shi, Tianyu Hu, Bo Yan, Song Wang, Yu Tian
cs.AI
Reasoning models often run into problems without noticing them, even when symptoms are visible in their own text. In humans, metacognition separates monitoring from control: fast, intuitive signals keep watch while slow, deliberate reasoning unfolds and help decide whether to continue, change course, or stop. System One (S1) decision models, such as Jev, are a natural candidate for this role: they return a calibrated probability for a...
-
07
LG-Bench: A Graph-Structured Evaluation Benchmark for Life Sciences
Lu Sun, Xiangyi Zhang, Xiangyang Zhu, Kaiyuan Ji, Zijian Chen, Qiang Hu, Zicheng Zhang, Yuan Tian, Guangtao Zhai
cs.AI
Traditional evaluation benchmarks reduce inherently interconnected scientific knowledge in life sciences into flat lists of questions, disregarding the underlying topological structure of the knowledge. We introduce, the first graph-structured benchmark for life sciences, featuring over 10,000 high-quality multiple-choice questions across medicine, biology, and chemistry. Our approach constructs a weighted evaluation graph using bidirectional...
-
08
Towards Robust Model Organisms for Eliciting Latent Knowledge
Lennart Finke, Hardik Bhatnagar, Euodia Dodd, Francis Rhys Ward, Yves-Alexandre de Montjoye, Matthias Bethge, Mary Phuong
cs.AI
A key problem in AI safety is eliciting latent knowledge (ELK), extracting information from a model that is misaligned and more knowledgeable than its overseer. For example, a misaligned model used to scan code for vulnerabilities may want to withhold its findings, i.e., sandbag, in order to exploit them later. To study ELK empirically, we need model organisms that mirror this setting. Existing model organisms fall short in several respects....
-
09
StepBench: Diagnosing Real-World Procedural Understanding in AI Agents
Hossein A. Rahmani, Bin Wu, Chaeeun Lee, Fanghua Ye, Sahan Bulathwela, Sujay Kumar Jauhar, Marzieh Fadaee, Nick...
cs.AI
Evaluating an agent's planning ability remains challenging for open-domain tasks, where verifying procedures through execution is often impractical. Existing evaluations typically assess only the final plan and do not distinguish procedural errors such as missing, incorrect, or misordered actions. We introduce STEPBENCH, a benchmark of 6,885 verified procedures crawled from wikiHow across 81 open-domain categories. From each procedure, we...
-
10
Honeypots for AI Agent Insider Threats
Jan Wehner, Jam Kraprayoon
cs.AI
AI agents deployed inside organizations can pose an insider threat if they make mistakes, are compromised by an attacker, or pursue misaligned objectives. We propose honeypots as an AI control method to improve the security of internal agent deployments. Rather than only using honeypots for pre-deployment evaluations, defenders should plant decoy opportunities for harmful actions throughout the production environment to detect misbehavior,...
-
11
AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes
Tian Zhang, Meng Li
cs.AI
LLM trading agents are evaluated almost exclusively in backtests and autonomous benchmark harnesses. Deployment, where actions are irreversible, raises a different question: who verifies the agent's actions, and which failures can each verifier structurally catch? We report on AllPath, a personal LLM trading agent deployed against a live paper-brokerage account. The system watches positions through a deterministic rules engine, and each night...
-
12
Tandem: Serving Hybrid Linear-Attention GUI Agents on Mobile NPUs
Zhuomin Chen, Jingchao Ni, Xu Zheng, Yong Chen, Mo Sha, Wei Cheng, Dongsheng Luo
cs.AI
Smartphone GUI agents complete tasks in mobile apps by repeatedly reading the screen and asking a model for the next action. Mobile neural processing units (NPUs) enable local execution, keeping screen contents on the phone, but model latency accumulates with every action. Hybrid linear attention models reduce memory requirements, yet reusing their recurrent state requires checkpoints at the appropriate input positions. Agent requests retain...
-
13
From Outcomes to Components: A Counterfactual Evaluation Framework for LLM-Proposed Repairs
Hengyu Ye, Songhua Hu
cs.AI · cs.CL
An LLM-generated repair action specifies which records to change and by how much. A failed action may still contain a useful target set or numerical update, depending on how the two are paired. We evaluate this problem in traffic networks and databases, where aggregate observations obscure the records that need correction. We examine the pairings by executing each combination from the same initial state, using a reference action that restores...
-
14
Revision-Based Learning from Interactive Experience and Feedback
Jiawen Li, Chenming Ge, Alice Gao, Rishab Vempati, Yi-Hao Peng, Jason Wu
cs.AI
Code generation models are increasingly used to produce interactive artifacts, such as websites and user interfaces. Many properties that determine whether these interfaces are useful only become apparent through realistic interaction, making them difficult to incorporate into model training. In this paper, we introduce RELIEF (REvision-based Learning from Interactive Experience and Feedback), a method for improving code generation models...
-
15
When the harness decides success: state that cannot be re-observed
Raimondas Lencevicius
cs.AI · cs.CL · cs.LG
Agent harnesses decide what a language model sees across turns: they drop old turns, summarize them, or replay the model's own earlier reasoning. We ask when these choices change whether an agent succeeds, not only what it costs, and report three findings. First, in a pre-registered synthetic probe, truncating the context window costs a low-cost reasoning model nothing in success when a needed fact can be looked up again (it looks the fact up...
-
16
WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting
Arjun Ashok, Mihir Parmar, Palash Goyal, Bhavana Dalvi Mishra, Chun-Liang Li, Irina Rish, Alexandre Drouin, Jinsung...
cs.AI · cs.LG · stat.ML
Recent time series foundation models (TSFMs) can consume covariates in-context, extending zero-shot forecasting to problems driven by external factors. This enables scenario analysis: forecasting how a target responds to events that set covariates to chosen future values. Whether they can do this reliably is an open question. We introduce WhatIf-Bench, a benchmark measuring how well forecasters use covariates to forecast a target's response...
-
17
Reward Objectives for Robust (PO)MDPs: A Law-Preserving Equivalence with (Partially Observable) Games
Durgam Latha, Dion Reji, Dorde Zikelic, Shankaranarayanan Krishna
cs.AI · cs.FL
Robust partially observable Markov decision processes model agents that act under partial observability while adversarial environment resolves uncertainty in the transition probabilities. Reward objectives such as discounted-sum, long-run average and cumulative reward under finite and infinite horizons allow quantifying the utility of an agent. We consider the problem of solving RPOMDPs under all four reward objectives, where the goal is to...
-
18
BetaMem: Learning to Remember a Changing World for Embodied Agents
Mai Liu, He Sun, Siru Zhong, Kerun Chen, Hao Yan, Xiaohui Lv, Shuai Tao, Wulong Liu
cs.AI
Long-horizon embodied agents face temporal confusion and incomplete or distorted records, recurring errors from fixed memory rules, and growing storage and retrieval costs. We present BetaMem, a framework for building and evolving traceable long-term memory through six linked layers: working, spatial, entity, episodic, experiential, and procedural memory. A dual-level write contract constrains operation executability and source support for...
-
19
Training Natural Schemers: RL Can Amplify Oversight-Conditional Behavior
Bart Jaworski, Nathaniel Mitrani, Fred Bruford, Victoria Krakovna
cs.AI · cs.LG
One of the central concerns for the safety of advanced AI is scheming: when a model strategically complies under oversight but pursues its own goals when unobserved. Current demonstrations, such as Anthropic's Alignment Faking work, depend on design choices that make them less convincing: explicit test-time prompting, handcrafted backdoors, or training data that demonstrates or hints at the target behavior. Model organisms built in this way...
-
20
Agentic Orchestration of EDC Data Space Retrieval and Natural Language Driven Data Processing
Marla Grunewald, Fin Gentzen, Iulisloi Zacarias, Admela Jukan
cs.AI
Participating in a data space still requires the Dataspace Protocol (DSP) negotiation flow to be hand-coded against each provider's access policy. We present a multi-agent architecture that automates this process using natural language requests. Built on LangGraph over an Eclipse Dataspace Components (EDC), the design separates concerns into cooperating agents. The orchestrator's role is to route and plan. The data extraction agent's role is...
-
21
Breaking Diffusion: Parallel Reasoning with Draft Refinement
Jaesang Yu, Seoyeon Byun, Yun Wang, Yan Lu, Juho Kim
cs.AI
Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually plausible token updates form a better answer together. We introduce Draft Refinement Language Models (DRLMs), which use a single denoiser to propose parallel revisions and evaluate a candidate draft. We train the denoiser to reconstruct every token from uniformly corrupted...
-
22
A Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes
Khaled Nowara, Mohamed Manzour, Catherine Elias
cs.AI · cs.LG
Knowledge graphs (KGs) are increasingly used in autonomous driving (AD) to make traffic scene entities and relations explicit for prediction and reasoning. Existing traffic-scene KGs, however, primarily emphasize trajectory forecasting or general scene understanding. This paper presents the nuScenes Intention Knowledge Graph (NIKG), a focused Web Ontology Language (OWL)-based semantic representation and construction pipeline for ego-centric...
-
23
Beyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulation
Jiajie He, Yuanhong Jiang, Xintong Chen, Dongling Ni, Wenjin Liu
cs.AI · cs.HC · cs.IR
Large language models (LLMs) are increasingly used as user simulators, but can they faithfully reproduce an individual's behavior and decision logic over time? We investigate this question in a longitudinal paper-trading study with 80 participants. Using rolling next-day predictions, we evaluate trading activity, buy-sell structure, asset selection, and portfolio outcomes, complemented by controlled input ablations and participant-rated...
-
24
Toward Structured Financial Foundation Models
Natraj Raman, Saumitra Mishra, Vamsi Potluru, Sumitra Ganesh
cs.AI · cs.CE
Foundation models promise reusable capabilities and step-change performance gains across tasks. In finance, large-scale pretraining of domain-specialized foundation models can advance both goals. However, prevailing architectures and objectives do not by themselves address the combined demands of financial systems: partial observability, interacting entities, asynchronous events, changing regimes, action-dependent outcomes, and rare states...
-
25
RouterWorld: Scaling Conversational AI with Latency-Aware LLM Routing
Jinyang Li, Denis Emelin, Simone Tedeschi, Weiwei Cheng, Cristina Morariu, Haytham Assem, Jens Lehmann, Emine...
cs.AI · cs.CL · cs.LG
Conversational AI systems built on Large Language Models (LLMs) require routing mechanisms that balance answer quality and response latency at scale. However, existing LLM routing benchmarks assume full observability of all candidate model outcomes, under-emphasize latency as a first-class metric, and fragment evaluation across heterogeneous protocols misaligned with real-world settings. We introduce RouterWorld, a comprehensive benchmark for...
-
26
ScopeMem: Latent Memory That Learns Where to Revise Frozen GUI Agents
Zhicheng Zheng, Cheng Zhang, Shengping Yu, Tianxiang Zhao
cs.AI
Latent memory is gaining ground as a lightweight history supplement for GUI agents. It supplies history to a frozen vision-language model via prefix vectors trained with step-wise cross-entropy (CE). While resulting gains are naturally attributed to encoded history, our controlled experiments show they primarily stem from action revision. The prefix learns to alter the model's default actions. However, this revision is unscoped because...
-
27
VeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards
Zhizhou Wang, Yaxi Lu, Zhong Zhang, Zikun Hu, Xin Cong, Yankai Lin, Fangming Liu
cs.AI · cs.LG
Reinforcement learning for computer-use agents increasingly relies on proactive reward agents that interact with the post-execution GUI environment to verify what recorded screenshots cannot reveal. The reliability of such verification hinges on two coupled decisions: what to check and when to stop. Existing methods leave these decisions to prompted foundation models. However, neither scaling up the model nor providing few-shot examples...
-
28
Remembering Has a Price: Learning Memory Worth under Resource Constraints
Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang, Han-Jia Ye
cs.AI
Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets. Under such stringent joint constraints, we find that existing lifelong-memory methods can become ineffective, with several sophisticated approaches offering little advantage over simple retrieval or even no-memory agents. This reveals a more fundamental problem:...
-
29
Physiology-Aware Graph Attention for Early Ventricular Reentry Prediction
Ma{ë}lis Morier, Jairo Rodr{í}guez Padilla, Patrick Gallinari, Maxime Sermesant
cs.AI
Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains difficult to predict from infarct imaging alone. While in silico induction studies can reveal these mechanisms, exploring many substrates and pacing locations remains computationally expensive. We propose a graph attention classifier for early prediction of sustained ventricular...
-
30
Local data augmentation for imbalanced binary classification
Harold Gu{é}neau, Alain Celisse, Pascal Delange
cs.AI · cs.LG · math.ST · stat.ML
Facing imbalanced binary classification, we aim at maximizing the recall while limiting the proportion of false detections in the minority class. For doing that, the present work studies the effect of several rebalancing strategies, from the uniform subsampling of the observations from the minority class, to a more involved local data augmentation scheme. To be more specific, we establish that only rebalancing class proportions cannot modify...
-
31
Answer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization
Yupeng Chang, Linyuan Gao, Zhiyuan Li, Yuan Wu, Yi Chang
cs.AI
An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finalization cue. On 100 fresh, independently audited GSM8K test questions per model, it improves delivered endpoint accuracy over first-box stopping by 8.0 percentage points for Qwen3-4B-Thinking-2507 and 7.0 for DeepSeek-R1-Distill-Llama-8B. A prelocked repeat on the same questions...
-
32
BOSS: Token-Budgeted Online Sampling and Selection for LLM Reasoning
Yupeng Chang, Yahan Li, Chenlu Guo, Diana Inkpen, Yuan Wu, Yi Chang
cs.AI
Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We study within-instance allocation: under a hard per-instance prompt-plus-completion token cap, when should inference stop, generate another candidate, or spend residual tokens adjudicating candidates already observed? BOSS is a training-free policy for this three-way decision,...
-
33
Autonomous intelligence for mining productivity: a multi-agent AI approach to operational value creation
N Guerin, A Dehoux, M Nakhla
cs.AI · cs.MA
Integrated Remote Operation Centres (IROCs) are emerging as the architectural frontier of Industry 4.0 for capital-intensive sectors such as mining, oil and gas, and energy. Yet two intertwined gaps constrain their evolution towards full autonomy. First, no integrated agentic architecture has been proposed for mining IROCs that orchestrates Supervisory Control and Data Acquisition systems, digital twins, predictive analytics and human-machine...
-
34
GAIDA: Generative AI for Human-in-the-Loop Document Annotation
Islam Mesabah, Ali Elhosary, Priyabanta Sandulu, Darko Obradovic, Sebastian J. Vollmer
cs.AI
Document annotation is a fundamental yet labor-intensive step in building document information extraction systems. While Optical Character Recognition (OCR) and Large Language Models (LLMs) can automate parts of this process, we argue that annotation systems should be judged not by how completely they remove human effort, but by how effectively they redirect it toward review and correction. We propose a modular human-in-the-loop architecture...
-
35
CARRS: A Constraint-Aware, Real-Time Routing System for Emergency Vehicles in Urban Environments
Vincent Sello, Timothy Adeliyi, Ridewaan Hanslo
cs.AI
Emergency vehicles such as police vehicles, fire engines, and ambulances require a stable and efficient route optimization to reach life-critical events in the shortest times possible. However, the dynamic nature of urban traffic makes this ideal scenario much more challenging, causing critical life-threatening delays. Traditional civilian navigation systems cannot account for real-time traffic changes alongside vehicle-specific constraints,...
-
36
VibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System Improvement
Ruotian Peng, Yuanyi Ren, Shuaiqi Liu, Xin Guo, Fang Zhu, Yangyi Huang, Yue Wu, Zheng Wang, Yandong Wen, Zhihang Fu
cs.AI · cs.CL
Recursive self-improvement (RSI) requires agents to diagnose system bottlenecks and coordinate improvements across training and inference. We refer to the agents' capability to jointly optimize training data, the trainer, and the inference harness as cross-component co-design. We introduce VibeTraining-Bench, a benchmark for evaluating this capability across tasks spanning terminal operation, software engineering, multi-turn tool use, and...
-
37
A Generic On-Board AI Processing Chain for Earth Observation: From Application Development to Embedded Deployment and Mission-Level Orchestration
Michel-Fran{\c c}ois Foulon, Liz Ramos Medina, Thomas Goudemant, Clotilde Szywala, Virgile Robles, Cl{é}ment...
cs.AI · cs.AR · cs.DC
Earth observation satellites acquire more data than they can downlink. Extracting information on board with artificial intelligence (AI) turns the satellite into a data-reduction stage that downlinks compact products, such as masks or detections, instead of full scenes; deploying it in a mission, however, involves the whole processing chain and not only the neural network. We present a generic on-board AI processing chain along three axes,...
-
38
The Control Layer Behind Rule-Following Agents Trading Across Market Conditions
Saad Naja, Nasser Odtallah, Jake Van-Praag, Sarah May
cs.AI · cs.LG · cs.MA · q-fin.RM · q-fin.TR
Trading discipline often fails people. Our study tested whether four AI trading agents followed their strategies and risk rules. Offering traders the evidence and an agent evaluation toolkit to separate luck from following the rules, before giving agents meaningful autonomy or capital. Our study analysed 2,627 closed positions from 12 February to 27 August 2026 across the same asset universe and execution conditions. Most positions were...
-
39
StrucChunk: Structure-Aware Retrieval for Legal Document RAG
Surya Deep Singh, Ashutosh Tripathi, Gaurav Deep Singh
cs.AI
Retrieval-Augmented Generation (RAG) can ground LLM outputs in domain-specific knowledge, but legal documents are hard: standard chunking fragments hierarchical argument structure, and generic embeddings struggle with both precise citation matching and semantic understanding. We propose StrucChunk (Structure Aware Chunking) with hybrid dense-sparse retrieval for hierarchically structured legal documents. It treats documents as directed...
-
40
Selective Transfer through Sequence Distillation: From Benchmark Knowledge to Backdoor Behaviour
Jonibek Mansurov, Sholpan Bolatzhanova, Filbert Aurelian Tjiaranta, Vallerie Alexandara Putra, Alham Fikri Aji
cs.AI
Knowledge distillation is widely used to transfer capabilities from teacher models to student models, but recent work shows that it can also transfer unintended teacher properties. We study whether different hidden teacher properties survive the same distillation channels. Specifically, we compare two properties: benchmark-associated knowledge and refusal backdoors, and show that distillation treats them very differently. Teachers fine-tuned...
-
41
The Scheduler Is a Hidden Retriever: How Asynchrony Shapes Evidence Acquisition in Search Agents
Ruiyang Ren, Yuhao Wang, Yinan Zhang, Chunyan Miao
cs.AI · cs.CL · cs.IR
Language-model agents increasingly solve complex tasks through parallel reasoning and asynchronous information gathering. Controlled replay across two model families and three benchmarks shows that delivery timing redirects search decisions made before all results arrive, despite identical initial evidence. Acquisition disagreement reaches up to 24 percentage points above same-order repeat variation. This dependence persists after all initial...
-
42
REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
Wanli Ma, Tianmeng Hu, Ke Li
cs.AI
RNA molecules often function through multiple experimentally observed conformational states. A central challenge is to capture ensemble diversity without sacrificing structural fidelity: samples may collapse toward averaged representative structures or drift into unsupported conformational regions. We introduce REFLEX (RNA Ensemble generation calibrated by FLEXibility), a sequence-conditioned generator for RNA backbone-frame ensembles based...
-
43
LOCU: Lowdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization
Joonyoung Lim, Younghwan Yoo
cs.AI
We investigate multi-constraint policy optimization in constrained Markov decision processes (CMDPs), where interactions among constraint gradients often yield ill-conditioned update directions, causing numerically fragile steps and unintended cancellation or redundant overlap in constraint corrections. To address this, we propose LOCU, which mitigates numerical instability arising from constraint interactions by applying symmetric Lowdin...
-
44
Beyond Static Leaderboards: Capability-Focused Evaluation with Structural Diversity for Time Series Foundation Models
Hongyin Zhang, Mingyi Xiang, Rongzhao Chen, Yankai Wang, Jialin Qiao, Xiangdong Huang, Xiaoou Ding, Chen Wang,...
cs.AI
Static public benchmarks for time series foundation models (TSFMs) typically have fixed and narrow test distributions. Their repeated reuse encourages benchmark-specific tuning, making reported performance reflect adaptation to the fixed test set rather than genuine forecasting generalization. In addition, a single aggregate score cannot fully characterize model capabilities across distinct temporal structures and input relationships. We...
-
45
Machina Pauliana: A neuro-symbolic approach to the actio pauliana in Dutch insolvency law
Daan Boven, Gregor Behnke, David Graus
cs.AI · cs.CL
Applying a legal provision frequently requires both structured rule-based reasoning and sensitivity to open-textured terms developed in case law. The actio pauliana of Article 42 of the Dutch Bankruptcy Act (Faillissementswet, Fw), which allows an insolvency practitioner to avoid transactions that prejudice creditors, requires both. We present a neuro-symbolic model of Article 42 Fw. Its symbolic core is written in Catala in a literate style...
-
46
CoRS: Fast Neural Flexible Job-Shop Scheduling via Composite Interval State Reuse
Jiang Sutong, Zhao Peng, Wu Xuan, Wang Yan, Wang Jiaqi, Zhang Rui, Jiang Yuan, Zhou You, Wang Di
cs.AI
Neural solvers for the Flexible Job-Shop Scheduling Problem (FJSP) typically refresh graph representations and update feasibility after every operation--machine decision. However, only feasibility must remain exact at every step, whereas graph encoding is substantially more expensive and can potentially be refreshed less frequently. We present CoRS, which decouples them: an interval-level graph representation is reused across multiple...
-
47
Towards More Granular Reasoning: Mapping the DSA Transparency Database Taxonomy to Platform Terms and Conditions Using Large Language Models
Alyson Ranucci, Eline Leijten, David Graus
cs.AI · cs.CY
Article 24(5) of the Digital Services Act (DSA) requires providers of online platforms to submit every content moderation decision they make, with a corresponding Statement of Reasons (SoR), to the DSA Transparency Database (DSA-TDB). Such decisions are classified against seventeen high-level attribute categories that categorize the primary reason for the moderation decision. Because over 99.8% of statements cite a violation of the provider's...
-
48
Fairness or Fallacy? Mapping the Landscape of AI Bias in Disease Detection
Ghulam Mudassir, Hameed Ullah Khan, Ahmad Sami Al-Shamayleh, Muhammad Faizan Khan, Muhammad Muqtasid, Moamin...
cs.AI
Artificial intelligence (AI) has several transformative effects on healthcare, like to facilitate clinicians in disease detection and to manage patient care with enhanced precision. Due to the increasing complexity of medical data and the growing volume of diagnostic images, the substantial computational power needed to process such information creates both opportunities and challenges. To accomplish this objective, numerous methodologies...
-
49
LLMs Prompted for Legal Context Refuse More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
Anastasiia Kucherenko, Francois Brouchoud, Dimitri Percia David, Andrei Kucharavy
cs.AI
Confidentiality requirements increasingly push legal professionals toward small, on-device LLMs that keep case data in-house, used for everyday tasks such as summarization, translation, and reformulation. Following standard prompting guidance, a user naturally states their role (``I am a lawyer...''). We show that this innocuous habit has an unexpected cost: such authority framing can make the model selectively refuse legitimate requests,...
-
50
On Counting Graphs for Modal Logic with Counting
Avijeet Ghosh, François Schwarzentruber
cs.AI · cs.LO
In this paper, we study the theoretical computational complexity of counting trees and graphs that are classified positively by a graph neural networks, or said equivalently that satisfy a given formula of modal logic with counting. We also study convergence.
-
51
MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
Yitong Li, Jiang Bian, Jingling Wang, Pan Ding, Chengying Gu
cs.AI
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable...
-
52
Reliable Before Profitable: QuantHarness for Governing Financial Strategy Development with LLM Agents
Jiasheng Mao, Jiacheng Liu, Hengwei Ye, Zheng Tian
cs.AI
LLM agents can turn natural-language financial research requests into executable and backtested strategies, but a successful run may still implement the wrong rule, use information unavailable at decision time, or obscure how repairs and candidate selection changed the strategy. Because these failures arise throughout development, final code and performance metrics alone are insufficient to establish either fidelity to the request or the...
-
53
From Code to Playable Systems: CEGame-Bench for Long-Horizon Game Creation Agents
Zixuan Dong, Yanghai Wang, Hanyan Bian, Jiaxi Tao, Junze Li, Jiadong Wang, Xinyu Che, Lin Liu, Baoyun Peng, Xiaodong...
cs.AI
A game ships when a player can launch it, finish it, and return to a saved world, none of which a successful build guarantees, yet game-creation agents are mostly tested on one engine or on one-prompt browser games. We present CEGame-Bench, the first long-horizon benchmark for complete-game creation across five production engines: Defold, Godot, Roblox Studio, Unity, and Unreal Engine. Agents build each game from an empty project and a design...
-
54
CUA-Lite: An Open Platform for Computer Use Agents
Zhanhui Zhou, Weichen Zhang, Haoran Liu, Lingjie Chen, Tianneng Shi, Kevin Lin, Zhengyuan Yang, Lijuan Wang, Dawn Song
cs.AI
Open resources for computer use agents (CUAs) -- environments, datasets, and models -- remain scattered: without a standard, these resources cannot be integrated and scaled; additionally, evaluation, RL, and SFT cannot share one infrastructure. We present CUA-Lite, an open platform for developing CUAs, built around three standardized abstractions: (1) Unified environment interface, under which we integrate 12 benchmarks across desktop,...
-
55
FinSafeGuard: A Quality-Driven Synthetic Dataset for Financial AI Safety
Joseph Thomas Thacil, Reetu Raj Harsh, Krati Saxena, Bhaskarjit Sarmah, Stefano Pasquali
cs.AI
Generating high-quality synthetic datasets at scale remains a fundamental challenge for training specialized AI systems in data-scarce domains. We present a comprehensive methodology that produces 14.3 million quality-filtered synthetic training examples from a structured taxonomy of 632,000 scenario specifications. Our four-stage pipeline ad- dresses critical challenges in synthetic data quality, diversity, and realism through: (1)...
-
56
Decision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems
Marco Polignano, Het Darshan Mehta, Pasquale Lops, Ernesto William De Luca, Giovanni Semeraro
cs.AI · cs.CL · cs.IR
Decision models, such as the commercial Jev, are language models that return one probability for each option of a question instead of generating text. We present Decision4Rec, an open and modular framework that makes decision models useful for recommendation. A knowledge graph writes the logs of each recommendation scenario as short statements on a defined scale, such as "sold: top 10%". A pool of agents, proposes candidates, and a residual...
-
57
AuDQ: Auditable Data Quality through Agentic Rule Discovery
Jacopo Biggiogera, Nicolas Colombo, Krati Saxena, Bhaskarjit Sarmah, Stefano Pasquali
cs.AI · q-fin.CP
High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as the LLM-era automation raises expectations for traceability and accountability. We propose a vision for an ontology-grounded, repository-native data quality layer in which rules are first-class artifacts: versioned, provenance-linked to governance texts, and re-playable...
-
58
Understanding When Reflective Prompt and Skill Optimization Helps on Locally Served Reasoning Models: A Two-Model Study of GEPA and SkillOpt
Andrea Giummarra, Carmelo Baglieri, Antonio Di Maria, Andrea Farruggio, Michele Piatto, Giovanni Micale
cs.AI · cs.CL
Reflective text-space optimizers such as GEPA and SkillOpt have reported large gains on frontier and mid-size models. We test replication across two reasoning-native target-serving configurations: DeepSeek V4 Flash through DwarfStar and Qwen3.8-27B through LM Studio. For each target, we evaluate the same held-out tasks and four conditions - minimal baseline, GEPA prompt, SkillOpt skill, and manually engineered prompt - on HotpotQA (n=500 per...
-
59
TimesJev: Thinking Fast on Time Series with System 1 Sufficiency
Chenghao Liu, Wei Fan, Jindong Han, Dongjie Wang, Aniket Mahanti, Pengyang Wang, Hao Liu
cs.AI
Large language models (LLMs) have recently shown strong potential for time series reasoning, while models that reason over time series are usually with long chains of thought. However, this process often consumes thousands of tokens, directly leading to substantial latency during inference. In contrast, System 1 models such as Jev make decisions instantly and can naturally be an alternative, but raw time series are not compatible with the...
-
60
Procedural Memory for Language Agents: A Neurosymbolic Perspective on Explicit Goal Structure
Jonathan Leung, Zhiqi Shen, Deheng Ye
cs.AI
Large language models remain unreliable on long-horizon tasks requiring procedural reasoning. We argue that a key cause is the absence of explicit procedural memory: accessible, modifiable knowledge of how tasks are accomplished, distinct from semantic and episodic memory. Goal-Oriented Graphs offer such a representation, encoding goals and prerequisite dependencies as inspectable symbolic structure. We examine their construction, the...
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.