cs.AI · 2026-08-17 · No. 87
Artificial Intelligence, 2026-08-17.
64 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
64 entries-
01
Handover of In-Context Learning State Across Session Boundaries
Masahiro Kato, Taka Kato
cs.AI · econ.EM · math.ST · stat.ME · stat.ML
This study investigates the methodological and theoretical properties of session handover in applications that use large language models. A task may continue in a new session when the context reaches the model's input limit, when the application restarts, or when another agent is asked to finish the task. The application must then decide which information from the earlier session to pass on. We formulate handover as the transfer of a...
-
02
Participatory Moral AI Is Not Neutral: The Invisible Hand of Developers
Taenyun Kim, Edyta Bogucka, Daniele Quercia
cs.AI
As AI systems make more morally loaded decisions across society, one response has been moral preference elicitation. In this approach, researchers poll participants on hypothetical dilemmas and use the aggregated votes to train a policy that an AI model then applies at scale. Before any vote is cast, developers make three key choices in the moral AI elicitation pipeline: feature scoping, voter sampling, and question framing. In other words,...
-
03
Split the Labor: Separating Evidence Interpretation from Decision Aggregation
Zhelun Wu
cs.AI · cs.CL · cs.LG
Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt. This conflates two operations with different requirements. Interpreting a source rewards capacity and context. Combining interpretations rewards fixed arithmetic, comparability across instances, and the option to return nothing. Once separated, the design problem becomes the interface between them. We propose a four-field...
-
04
Twin: Playing an Unknown Game with a Test-Time Digital Twin
Alexy Skoutnev, Kirill Acharya, Gaston Longhitano, Madeleine Udell, Kevin Ellis, Iddo Drori
cs.AI
We present a Test-time World-model Inference (Twin) system, in which a frontier coding agent writes an executable world model for completing continual learning tasks, such as ARC-AGI-3 games. Traditional approaches hand-engineer such models, one custom design per task. Each game hides its rules and goal, and our system constructs them from simulation and interaction alone. Its inductive prior over grid games is strong enough to recover the...
-
05
Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments
Shahab Band, Hamed Mohammadi
cs.AI
Short-horizon forecasting of fine particulate matter (PM2.5) remains difficult when observations from the target domain are limited and the statistical properties of the source and target domains differ. In these settings, models trained only on local data may not capture complex temporal dynamics, while direct transfer learning can result in negative transfer. This study develops a shift-aware dual-encoder transfer framework that combines...
-
06
SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
Panjing He, Mingyue Cheng, Yucong Luo, Li Li, Xiaohan Zhang
cs.AI
Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Real-world workbooks often contain implicit cross-table associations, fine-grained column dependencies, and complex spatial layouts. Existing methods typically flatten these multidimensional structures into sequential strings, losing important intra-sheet boundaries...
-
07
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports
Beatrice Alessandra Motetti, Emilien Guandalino, Daniele Jahier Pagliari, Alessio Burrello, Lorenz K. Müller,...
cs.AI
In the current artificial intelligence-driven innovation era, the pace of knowledge growth is accelerating, and is hard to keep up with. While generative models are increasingly used to synthesize content, they often lack in information grounding. To address these peculiarities of our time, we propose Wyvern, a multi-agent framework for the automated generation of grounded, multimodal technical reports. Wyvern allows for the generation of...
-
08
PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
Yuhao Zhan, Bingxiang He, Zecong Tang, Chaojun Xiao
cs.AI
Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions and do not test recovery after those conditions change. To address this gap, we introduce PACE-Bench (Physics Adaptation via Code Evolution), a simulator-grounded benchmark of 144 source-to-target adaptation pairs across six physics domains. Each pair links a source environment to a mutated...
-
09
The Dynamics of Intelligence Explosions
Toby Ord
cs.AI · econ.TH
AI is increasingly being used to help with AI R&D. Under certain conditions this feedback loop might be able to produce an intelligence explosion, with rapidly escalating AI capabilities. I explore the mathematics of the most explosive possibilities, with an eye to understanding what drives the dynamics. I show that singular growth (towards a vertical asymptote) is harder to achieve than would be expected from recent economics-inspired...
-
10
Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations
Toby D. Pilditch
cs.AI
LLM evaluations often use fixed sampling budgets, testing every item the same number of times even after estimates are precise. We introduce optstop, a precision-based adaptive stopping framework that treats evaluation as a sequential measurement problem: keep sampling where uncertainty remains high, and stop where estimates are precise or stable enough. The framework builds on hierarchical Bayesian inference, supports binary, ordinal, and...
-
11
The Past and Future of AI Scientists
Ross D. King
cs.AI
We present a survey of the past and future of AI Scientists: machines capable of automating science. AI Scientists can originate hypotheses, deduce their consequences, design and execute experiments, interpret their results, and revise their beliefs. Such systems are integrated scientific agents, connected to the literature, formal knowledge, mathematical models, simulations, data-analysis systems and physical laboratories. Adam was the first...
-
12
LLMs Don't Pay for the Jump
Paras Balani, Subhrakanta Panda
cs.AI · cs.CL
Zahavy [2026] argues that Large Language Models, despite their capabilities in induction and deduction, cannot perform the abductive "Jump" that produced Einstein's equivalence principle, and attributes this limitation to the absence of embodied simulation. Zheng-Xin [2026] and Farmer [2026] question whether embodiment is necessary for abduction, pointing to alternative routes to General Relativity and forms of abduction that require no...
-
13
Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons
Wei Zhao, Zhe Li, Peixin Zhang, Jun Sun
cs.AI
Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this promise, i.e., they often compromise model utility significantly. Specifically, one line of work suppresses toxic neurons to erase harmful semantics, but since such semantics are distributed across the network, blocking every pathway forces a large intervention...
-
14
AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
Yu Zhuang, Kefei Chen, Yitong Duan, Shuxin Zheng, Jian Li, Xu-Yao Zhang
cs.AI
Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may propagate through both the agent context and environment state, and their effects may be difficult to reverse through subsequent actions. Existing methods mainly seek to reduce such errors through plan refinement and safety checks but provide little support after errors occur. To enable recovery...
-
15
Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang, Weijian Zheng, Fernando Llorente, Xiaolong Ma, Xinyang Li,...
cs.AI · cs.CL · cs.LG
Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently...
-
16
Designing Sustainable Federated Learning as a Service using Neural Architecture Search
Keya Patel, Sajib Mistry, Sheik Fattah, Deepak Kanneganti, Aneesh Krishna, Mufti Mahmud, Monowar Bhuyan
cs.AI
The sustainability constraints of FLaaS consumers pose significant challenges to maintaining carbon-feasible federated training in FLaaS environments. These constraints often lead to infeasible consumer participation and unstable federated training under hard carbon constraints. We propose a Sustainable Federated Learning as a Service (SFLaaS), a carbon- constrained Neural Architecture Search (NAS) framework for heteroge- neous sustainable...
-
17
Disentangled Shared Representations Improve Morpho-Transcriptomic Integration
Julian Ostermaier, Swann Ruyter, Reuben Dorent, Daniel Racoceanu
cs.AI
Spatial transcriptomics (ST) enables the simultaneous profiling of gene expression and tissue morphology, creating an opportunity to learn multimodal representations capturing shared morpho-transcriptomic structure. However, standard multimodal models often compress modalities into a common latent space without explicitly separating shared and modality-specific sources of variation, which may limit downstream utility. We investigate whether...
-
18
ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond
Mingming Zhao, Jiqian Dong, Kangping Xu, Zadid Hasan, Chengrui Fan, Shan Jiang, Shuai Mao, Ting Lingya, Linyi Zou,...
cs.AI
Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources. Pioneering autoresearch agents, despite great success, still lack mechanisms for continuity, recovery from dead ends, and value-driven compute...
-
19
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
Zhizhao Guan, Chen Huang, Ziming Liu, Hongru Liang, Wenqiang Lei, See-Kiong Ng, Tat-Seng Chua, Anthony G Cohn
cs.AI · cs.LG
We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire information that improves future decision-making. In this regard, we first identify two fundamental bottlenecks that hinder this capability and then propose \ours, a novel method designed to instill and refine proactive exploration. Specifically, \ours\ consists of two components: (1) Exploratory Data Construction, which synthesizes...
-
20
Program-space Diffusion for Morphology-to-Transcriptomics Prediction
Ruyter Swann, Dorent Reuben, Racoceanu Daniel
cs.AI
Spatial transcriptomics (ST) enables genome-wide gene expression profiling while preserving tissue architecture, but its cost and limited scalability remain major bottlenecks. This has motivated models that predict spatial expression directly from routine histology. Despite promising results, most existing approaches operate at the gene level without leveraging established transcriptomic modeling practices and rely on heterogeneous gene...
-
21
AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
Yiderigun Borjigin, Alexander Hermann, Christian Cyron, Roland Aydin
cs.AI · cs.CL
The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself. This effect is well established in human judgment and decision-making, and recent work suggests that large language models (LLMs) exhibit similar behavior. However, existing work on anchoring in LLMs typically evaluates only a narrow set of anchor pathways and rarely distinguishes irrelevant from plausible anchors. We introduce...
-
22
Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety
Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi
cs.AI · eess.SY
This paper presents a coordination architecture for heterogeneous UAV/UGV swarms that synthesises mission actions from uncertain, multi-modal sensor evidence while preserving hardware-enforced safety at the actuation boundary. The approach combines radar, RF, acoustic, and visual observations with Topic-Based Communication Space Petri Net (TB-CSPN) orchestration to support incremental mission formation under partial and evolving information....
-
23
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
Kai Chen, Jifeng Ding, Ning Ding, Jiaye Ge, Lixin Gu, Yicheng Gu, Qipeng Guo, Ermo Hua, Haian Huang, Haozheng Hou,...
cs.AI
We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning. Using hidden states as cache and carrier, reasoners repeatedly query memory for required knowledge-vectors, while the knowledge is transmitted back to reasoning operators. Through this knowledge-reasoning-separation architecture, Mobius achieves...
-
24
TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments
Qingren Yao, Yaxuan Kong, Yuqi Nie, Yichen Li, Stefan Zohren, Anna Vettoruzzo, Qingsong Wen, Ming Jin, Joaquin Vanschoren
cs.AI
Time series analysis in high-stakes domains relies on recurring data releases, where new observations can alter the evidence base and the validity of later conclusions. Existing time series QA benchmarks mostly rely on fixed snapshots, leaving temporal validity and cutoff-aware evidence use unevaluated. We introduce TimeSage-EV, a live benchmark for agentic time series analysis in evolving environments. It tracks 60 real institutional...
-
25
Grounding Without Corrective Control: Truth-Tracking Profiles for Large Language Models
Brett Reynolds
cs.AI · cs.CL
Recent work suggests that some large language model representations have content or reference. Grounding can secure either without supplying live routes for correction. This paper asks what follows from that gap. An output is answerable when discrepancies can affect what a target- and task-specific arrangement produces, accepts, or withdraws. The arrangement has corrective control only when live, sufficiently independent routes can detect and...
-
26
Polaris : Multi Agentic System for Conversational Enterprise Analytics
Varuni H K, Soham Sarkar, Jay Kumar, Goutham Krishnan, Tanvi Johari, Avinash Bharadwaj, Santosh Hegde
cs.AI
In today's fast-paced environment, the ability to swiftly access, understand, and act on data is no longer optional; it is essential. Yet most organizations remain data-rich but insight-poor, constrained by the complexity of querying, interpreting, and explaining enterprise-scale information. We present Polaris, a supervisor-led multi-agent framework for conversational enterprise analytics that bridges this gap. Polaris introduces Dynamic...
-
27
Attributing Preprocessing Invariance in Spectral Foundation Models
Dongjun Wei, Hongyi Wu, Yinuo Zou
cs.AI · cs.CE · cs.LG
Preprocessing invariance is an appealing goal for spectral foundation models: a frozen model should remain useful when laboratories preprocess spectra differently. It is usually measured by training a classifier under one preprocessing pipeline and testing it under another, with preserved accuracy read as evidence of learning. We revisit that reading, using a Raman foundation model as a case study. Such models normalize their inputs before...
-
28
MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement
Lushi Pu, Weiming Zhang, Xinheng Xie, Zixuan Fu, Bingxiang He, Hengyu Zhao, Hongya Lyu, Xin Li, Jie Zhou, Yudong Wang
cs.AI · cs.CL
Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4. However, faithful formalization requires more than translation. Models must map mathematical concepts to the complex hierarchy of types and definitions in formal libraries such as Mathlib, while ensuring that generated statements preserve the meaning of the source propositions. Existing...
-
29
A Generalized Parallelogram Rule for Proportional Analogies on Riemannian Manifolds
Pierre-Alexandre Murena, Marcelo Hartmann
cs.AI
Analogies are quaternary relations of the form "a is to b as c is to d", usually denoted a : b :: c : d. This notion is formalized in particular with the notion of proportional analogy, which imposes some constraints on the valid analogies. Whereas proportional analogies have been studied mostly in symbolic domains and in vector spaces, their use is limited in non-Euclidean spaces. In this paper, we introduce a proportional analogy relation...
-
30
APTER: Adaptive Post-Training with Expert-Grounded Rubrics
Xukai Wang, Liangqi Li, Zhiyue Xu, Jingang Zhou, Xiaoyu Shi, Jiansheng Cai, Bo Zhang, Zhe Li, Xu-Yao Zhang
cs.AI
As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses. Existing post-training methods often rely on holistic preferences or outcome-level verification, while recent rubric-based methods usually generate rubrics independently for each query. In specialized domains, such unconstrained rubrics may omit...
-
31
FreeBalance: Pre-Routing Online Moe Load Balancing via Residual Workload Prediction
Pengfei Chen, Yize Wu, Shouxu Kuang, Ke Gao, Ling Li
cs.AI · cs.LG
Load imbalance poses a major bottleneck to the efficiency of expert parallelism in distributed inference of Mixture-of-Experts (MoE) models. The most heavily loaded rank stalls global execution due to skewed routing distributions, directly increasing latency. While offline expert placement can alleviate persistent imbalance, practical multi-task serving workloads exhibit layer- and batch-dependent routing dynamics, making online load...
-
32
Can Language Models Understand mmWave Data? Benchmarking Large Language Models for mmWave Radar-Based Human Understanding
Jeongwan Shin, Jaehyeon Kim, Donguk Ko, Jaeho Choi
cs.AI
Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for perception. While modern approaches such as vision-language models (VLMs) have attempted to incorporate reasoning capabilities into visual sensing, the integration of LLMs with the millimeter-wave (mmWave) modality-despite its unique advantages under low light and occlusion-remains largely...
-
33
BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs
Varsha Ramineni, Hossein A. Rahmani, Jerome Ramos, Karin Sevegnani, Emine Yilmaz
cs.AI
LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications. While prior work has made progress in measuring and mitigating bias, it largely focuses on final outputs of models, with limited understanding of the mechanisms that produce biased outcomes. Recent advances in LLM reasoning offers a new lens for investigating bias, yet the link between reasoning and bias remains...
-
34
Removing Temporal Note Redundancy Improves Multimodal Reinforcement Learning for Medicine
Chenran Weng, Joo Seung Lee, Malini Mahendra, Anil Aswani
cs.AI · cs.LG
Mechanical ventilation is a critical life-support intervention, requiring dynamic adjustments to ventilator settings as a patient's condition evolves. While reinforcement learning (RL) offers a promising framework for optimizing these sequential decisions, standard approaches rely primarily on structured electronic health record (EHR) data, missing crucial clinical context recorded in free-text notes. Integrating longitudinal clinical notes...
-
35
Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based Fine-Tuning Approach
Sheng Hong, Xuanqi Wang, Jiacheng Wang, Yuwei Wang
cs.AI
Recent advances in large language models (LLMs) have reshaped semantic analysis. Opinion Extraction (OE) for Science and Technology Intelligence (STI) requires concise core opinions from large information streams. Off-the-shelf models struggle to filter noise from these streams and show limited structured-output reliability in zero-shot multilingual and multi-modal settings. To address information overload and extraction defocus, this study...
-
36
QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation
Lin-Fa Lee, Yi-Yu Chang, Kuo-Hei Yeh
cs.AI · cs.CR
Recent training-free post-training quantization methods restore model accuracy through closed-form residual compensation. To constrain additional model storage overhead, several existing methods gate layer selection by goodness-of-fit, retaining only those layers whose compensation yields a positive residual fit score and discarding the rest. In this paper, we show that, under the low-bit W4A4 setting, this gating mechanism fails to...
-
37
Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Cost
Xiaodi Huang, Ziyi Ding, Jingtian Wan, Yuchen Liu, Yuan Zhang, Xiao-Ping Zhang, Jiayu Chen, Zhang Zhang, Tao Huang
cs.AI
LeWM is a lightweight visual world model that learns latent dynamics end-to-end from pixels and ranks candidate action sequences by the distance between their predicted endpoints and the goal. However, LeWM has two limitations. First, during training, it learns local next-step transitions without evaluating complete trajectories relative to the task goal. Second, during planning, it ranks candidates solely by predicted endpoint distance....
-
38
Reinforcement Learning-Based Production Scheduling in an Industry-Based Coating Scenario Using the Digital Model Playground
Arne Kröger, Ralf Buschermöhle, Wilhelm Hasselbring, Henrik Wilbers
cs.AI
Production scheduling in complex manufacturing environments is challenging when sequence-dependent setup times, stochastic disturbances, and due-date constraints must be addressed simultaneously. While reinforcement learning (RL) methods have shown promising results in research, most studies rely on simplified benchmark processes, limiting their industrial relevance. This paper demonstrates the applicability of RL-based scheduling in an...
-
39
A Graph-Based Reinforcement Learning Framework for Structured Drift Diagnosis and Recovery in Autonomous LLM Agents
Ismail El Hamraoui, Sagar Jose, Nicolas Bureau, Robert Plana
cs.AI · cs.LG · cs.MA
Autonomous LLM agents are increasingly deployed in complex real-world workflows, yet they remain vulnerable to runtime behavioral drift, a silent deviation from the original task that can lead to irreversible side effects on external systems. Existing approaches address drift at the prompt level but lack structured mechanisms for step-level detection, risk assessment, and recovery decision. Because the main task-executing agent is often a...
-
40
Retrieval Grounding Latent Reasoning for Dense Retrieval
Gang Zhou, Xiongxi Yu, Hu Tian, Yang Wei, Lu Pan, Ke Zeng, Shibiao Xu, Xiaolong Zheng
cs.AI
Reasoning-intensive retrieval requires text representations to capture not only semantic similarity, but also the reasoning needed to determine relevance under a given retrieval instruction. Existing reasoning-enhanced embedding models improve retrieval by incorporating reasoning information into dense representations, yet their supervision is typically dominated by the final retrieval objective. As a result, latent reasoning trajectories may...
-
41
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Thiago Sandoval, Ufuk Topcu
cs.AI · cs.CL · cs.CR · cs.LG
Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves. We present Regime-Conditional Verification (RCV), a lightweight wrapper that adapts an off-the-shelf safety classifier without retraining it. RCV estimates, from the classifier's internal...
-
42
A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images
Jennifer D'Souza, Fahad Ahmed, Cecilia Andrea Bustamante Andrade, Lina Frolova, Poorani Gnanasambandan, Dilshad...
cs.AI · cs.CV · cs.DL
Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret. The ALD/E-ImageMiner benchmark and ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching Scientific Figures provide 1,951 figures from 205 publications, expert-annotated for classification, data table extraction, summarization, and visual question...
-
43
Mandato: Protocol-Level Enforcement of Digitally Signed Mandates on AI Agent Actions with Cryptographically Chained Audit Trails
Giovanni Racioppi
cs.AI
AI agents increasingly act on external systems through standardized tool-calling protocols such as the Model Context Protocol (MCP), yet no infrastructure layer constrains their actions to what a principal has verifiably authorized: authorization logic lives in application code, is neither signed nor independently auditable, and the resulting logs lack evidentiary value. We present Mandato, a governance proxy that enforces digitally signed...
-
44
Scaling Domain Data Repetition in LLM Pretraining
Jingwei Li, Xinran Gu, Rui Dai, Xintong Hao, Chengyin Xu, Yan Wu, Shuran Zheng, Jingzhao Zhang
cs.AI
As large language models scale, their training-token budgets must also increase to maintain an appropriate tokens-per-parameter ratio (\(\mathrm{TPP}\)). However, high-quality domain data is much harder to scale than general web data. As model size and the training-token budget increase, its fraction in the training mixture tends to decrease. Repeating the available high-quality data provides an effective way to counteract this dilution, but...
-
45
Benchmarking data-driven material models on the classic Treloar dataset
Hagen Holthusen, Moritz Flaschel, Denisa Martonová, Ellen Kuhl
cs.AI · cs.CE
Machine learning is rapidly reshaping constitutive modeling, offers new ways to learn material behavior directly from experimental data, and challenges long-established modeling paradigms. But with a growing number of machine-learning-based approaches available, how do they compare in practice? In this paper, we use the classic experimental data of Treloar to benchmark popular frameworks for hyperelasticity: (Generalized-Invariant)...
-
46
Demystifying Agent Skills: Why They Work-Until They Don't
Zhiyuan Jiang, Fangrui Huang, Hanwen Xing, Xander Wu, Yipeng Gao, Rui Cao, Mengdi Wang, Shilong Liu, Yijiang Li
cs.AI
Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge. However, existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: \emph{\textbf{When do skills help, why do they work, and where do they fail?}} Through controlled experiments across various benchmarks, agent harnesses and...
-
47
Agent-Orchestration in Autonomous Chip Design
Linyang Li
cs.AI
Recent developments in large language models (LLMs) and tool-using agents encourage people to explore the potential of using agents in chip design. The core question is what kind of AI we really need in such a sophisticated industry. To this end, we bring the idea of modeling a chip-design superintelligence as an enormous \textit{AI-organization}.
-
48
Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders
Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama
cs.AI · cs.IR
Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expressed in the representation used for prediction remains unclear. We combine prediction-time diagnostics with norm-based analysis of the full attention block. First, we show that SASRec-style models exhibit highly localized last-item reliance. We then find that,...
-
49
Buy the Rumor, Sell the News: When Is News Priced In?
Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini, Sid Ghatak, Arman Khaledian
cs.AI · cs.LG · q-fin.ST
Two old market sayings hold that news is already priced in by the time it is published, and that the rumor is bought while the news is sold. Both place the price move associated with a piece of news before and at publication rather than after it. Whether the claims hold, for which kinds of news, and by how much are basic questions about how fast markets absorb public information. We test them on 4.57 million financial news articles covering...
-
50
Simulation-Driven Vehicular Traffic Data Augmentation: Extending Sensor Coverage Through Virtual Sensing
Davide Andrea Guastella, Eladio Montero Porras, Evangelos Pournaras, Gianluca Bontempi
cs.AI
Urban traffic management relies on sensor networks whose spatial coverage is limited by deployment costs and privacy regulations. Machine learning models trained on such sparse data cannot generalize to unmonitored locations and must be retrained whenever the sensor infrastructure changes. We propose a simulation-based methodology that addresses this problem by generating augmented traffic count datasets in which each physical sensor is...
-
51
Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy
Liwei Deng, Jing Jiang, Zhiwei Li, Yang Wang, Guodong Long
cs.AI · cs.IR
Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capture attention within seconds. These systems inherently favor shallow-content videos that are effective at attracting immediate attention. However, growing evidence suggests that prolonged exposure to such content may negatively affect users' cognitive engagement and mental well-being, raising...
-
52
Nanbeige4.2-3B on Apple Silicon: Fixing Deployment Bugs and Decreasing Looped Transformer Memory Overhead
John T. Halloran
cs.AI · cs.LG
Nanbeige4.2-3B is a 3B-parameter agentic model built around a Looped Transformer (LT) that reuses one stack of layers for a second forward pass, adding effective depth without additional parameters. Evaluated on Apple Silicon (MPS), we identify five independent bugs which prevent the released checkpoint from running via Hugging Face transformers out of the box (including a silently-zeroed RoPE buffer and calls to removed transformers cache...
-
53
Implementing Computational Law in Wolfram Language for the Governance of Artificial Intelligence
James K. Wiles
cs.AI · cs.CY · cs.LO
How do we govern AI systems whose reasoning we cannot fully inspect? Governance does not require understanding a system's reasoning. It requires stating what the system is obliged, permitted, and forbidden to do, and checking whether it complied. I present an implementation of Reified Input/Output Logic, the formalism behind the DAPRECO knowledge base, in Wolfram Language: the core I/O axioms, obligations, permissions, constitutive norms,...
-
54
HELIX: Model-Harness Co-evolution for Recursive Self-Improvement
Tianyu Fan, Chao Huang
cs.AI
Scaling agent capability has largely focused on improving the model, yet an interactive agent acts through a runtime harness that mediates context, tools, control flow, and stopping. The harness shapes both what a model can accomplish and the trajectories from which it learns. This coupling motivates model-harness co-evolution for recursive self-improvement: build harnesses for a fixed model, update the model from verified sibling...
-
55
AI Research Preference Models
Thomas Simon Foster, Bassel Al Omari, Tingchen Fu, Thomas Mann, Carl Domond, Lucia Cipolina-Kun, Bhavul Gauri, Muna...
cs.AI
AI research agents (AIRA) can now propose, implement, and evaluate their own machine learning experiments, but progress on frontier tasks is throttled by cost: a candidate solution can be written in minutes, whereas evaluating it can take hours to days of GPU time. An agent can therefore propose far more candidates than it can afford to run, and its progress depends on its research preference: how it allocates a fixed execution budget across...
-
56
Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact
Zhelun, Wu
cs.AI · cs.CL · cs.DB
Large language models have made natural language interfaces to databases (NLIDB) newly credible, but LLM text-to-SQL systems fail in a way that matters for deployment: a hallucinated column or a mis-aggregated total yields a fluent wrong answer, indistinguishable at the point of use from a right one. Where the consumer cannot inspect the generated query, as in enterprise AI deployments and operational dashboards, and increasingly where the...
-
57
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
Lu Yang, Shusheng Xu, Zhuoran Li, Tongkai Yang, Longbo Huang
cs.AI
LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks context, time, or source authority to interpret conflict, treating one memory as definitive converts unresolved conflict into an unjustified, overconfident action. Existing benchmarks recover one answer from conflicting evidence, overlooking whether agents...
-
58
MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends
Chaoqun Zhan, Qiang Zhou, Guannan Li, Zhenqiang Huang, Qianjin Wang
cs.AI
Most agent-memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether memory supports interdependent, multi-session task completion. We compare MemoryLake, a structured multi-track memory backend, with Mem0, text-embedding-3-small vector RAG, and a long-context control across all five MemoryArena domains. The systems share the same agent framework, requested gpt-5-mini model alias, task samples, and scoring code; the memory...
-
59
Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference
Yunchu Han, Zhaojun Nan, Sheng Zhou, Zhisheng Niu
cs.AI
Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and memory resources. To enable energy-efficient DNN inference, most existing studies focus on dynamic voltage and frequency scaling (DVFS) for adjusting the computing frequency, while the impact of memory frequency on the inference performance has been greatly overlooked. In this paper, we consider the impact of...
-
60
SDO: Subspace Deconflicting Operator for Multi-Adapter Composition
Zhongsheng Wang, Zhedong Lin, Qian Liu, Xinyu Zhang, Jiamou Liu
cs.AI
Composing independently trained adapters within a shared diffusion backbone provides a modular approach to multi-character generation, but naive joint deployment often causes identity mixing, cross-character attribute leakage, and unstable scene composition. We study this interference from a parameter-space perspective and hypothesize that it arises partly from conflicts between overlapping dominant subspaces in shared layers. To address this...
-
61
From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL
Wenyue Hua, Zachary Huang, Tyler Payne, Safoora Yousefi, Saleema Amershi, Asli Celikyilmaz
cs.AI · cs.CL · cs.LG · cs.MA
AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices. These principal-driven tasks routinely place the agent across from a counterpart (another user's agent, a seller, a recruiter) whose goals may conflict with its principal's. Yet the dispositions that make an assistant pleasant can make it a poor delegate: a friendly, helpful frontier model may disclose its...
-
62
FLARE MCMC: Fidelity-based Layer-Adaptive REcursive proposals for MCMC
Harini Venkatesan, Christian Shelton, Ming-Feng Ho, Simeon Bird, Mengxuan Wu
cs.AI
Markov chain Monte Carlo (MCMC) requires only the ability to evaluate the likelihood, making it a common technique for inference in complex models. However, it can have a slow mixing rate, requiring the generation of many samples to obtain good estimates and an overall high computational cost. FLARE MCMC is a multi-fidelity layered MCMC method that exploits lower-fidelity approximations of the true likelihood calculation to improve mixing and...
-
63
Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement
Bingyang Liu, Ziming Wei, Xiaohan Gao, David Z. Pan
cs.AI · cs.RO
Analog IC layout design remains a labor-intensive iterative process dominated by simulation-driven refinement. Although end-to-end layout generators accelerate initial placement and routing, they still require experts to manually tune layout optimization parameters with repeated post-layout simulations for stringent design specifications. While Bayesian Optimization (BO) is widely adopted for parameter tuning in analog IC design, at the...
-
64
Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defensible Analytic Variation
Ajay Pravin Mahale
cs.AI
The EU AI Act requires providers of high-risk systems to file technical documentation describing how the system reaches its decisions. Mechanistic interpretability is the obvious source of such evidence, and circuit discovery is its most developed instrument. We ask whether that evidence survives the condition under which it would be relied upon: two competent analysts, the same system, the same tool, different defensible settings. We...
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.