cs.AI · 2026-11-16 · No. 173
Artificial Intelligence, 2026-11-16.
56 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
56 entries-
01
Imitation Bootstrapped Multi-Agent Reinforcement Learning
Tony H. Zhang, Connor Mattson, Daniel S. Brown
cs.AI · cs.MA
Demonstrations are an effective way to accelerate single-agent reinforcement learning (RL), but extending this idea to multi-agent reinforcement learning (MARL) is non-trivial as it is difficult and often impossible for a single person to teleoperate multiple agents simultaneously. Round-Robin Behavior Cloning (R2BC) addresses this by letting a single demonstrator control one agent at a time while the others execute their current policies....
-
02
ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL
Zelin He, Siyu Zhu, Jacob Helwig, Yujian Liu, Li An, Rohit Jain, Shiyu Chang, Alborz Geramifard
cs.AI · cs.CL · cs.LG
Agentic reinforcement learning (RL) increasingly relies on a harness, the scaffold around the model that decides what it sees of its own interaction and what guidance it receives. Most existing approaches train under a hand-written harness that stays fixed throughout. However, an effective harness depends on the domain, the data and the model, and keeps changing as the model trains. We introduce ModHarness-RL, which recasts the harness as...
-
03
Alignment by Socialization: Learning Tradeoffs Under Selection
Thomas Brennan, Andrew W. Lo, Chaoyi Zhao
cs.AI · q-bio.PE · q-fin.GN
Artificial intelligence (AI) agents are expected to complete tasks while following rules of conduct, but these objectives can conflict. We study how evolutionary selection shapes an agent's choices between them, and whether experience can make those choices reflect human judgments and withstand subsequent pressures. In our model, copies of an agent face a common uncertain reward state, and only those taking the rewarded action reproduce. We...
-
04
Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination
Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao
cs.AI · cs.CL
Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face when applied to realistic agentic failures. We focus on one such failure: web agents hallucinating actions that are not...
-
05
ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models
Dhruv Dixit, Khushi Patel, Congcong Xu, Min Song
cs.AI
Small language models are attractive for local, low-cost, and privacy-sensitive deployment, but they remain unreliable on mathematical reasoning tasks that require decomposition, exact computation, tool use, and verification. We introduce \textbf{ARCHER}: \textbf{A}ction-trace \textbf{R}einforcement for \textbf{C}alculator-grounded \textbf{H}ierarchical \textbf{E}xecutable \textbf{R}easoning, a two-stage framework for training small language...
-
06
Typing Matters: Muscle, Language and Typing Behaviour in Live Keystroke Decoding from sEMG
Abhilash Durgam, Nyle Siddiqui, Mubarak Shah, Qiushi Fu
cs.AI
Surface electromyography (sEMG) from the wrists can recover typed text without a keyboard. It is usually posed as a signal-inference problem: characters are read out of the muscle signal and character error rate is reported offline. We argue that this framing removes most of the problem. The decoder is constrained simultaneously by the muscles, by the language being typed, and by typing behaviour such as typos, corrections, backspaces and...
-
07
When to Trust Simulated Patient Responses:Support-Gated World Models for Vasopressor Decision Support
Yifan Jin, Tao Liu
cs.AI
Clinical world models expose language-model agents to predicted patient responses, but simulations can be unreliable for poorly supported treatments or unfamiliar hospitals. We introduce Support-Gated World-Model decision support, a lightweight extension of a propose--simulate--refine agent. A recurrent dynamics ensemble predicts short-horizon physiological responses to documented norepinephrine dose categories, while a behavior model...
-
08
Towards Explainable Sleep Stage Classification using Single-Channel Electroencephalogram
Gurinder Kaur Sandhu, Jude Koenig, Ankita Shukla, Shruti Kshirsagar
cs.AI · eess.SP
Automated sleep staging has achieved strong bench- mark accuracy; however, clinical adoption remains limited due to a lack of interpretability. In this work, we fill the research gap by extending the SleepXAI sleep staging framework to systematically compare five different XAI methods. Further, attribution fidelity is evaluated using Spearman rank correlation with AASM-defined EEG frequency bands, serving as clinically grounded reference...
-
09
LECAT: Measuring LLM Category Learning from Pretraining Data
Jimin Mun, Maarten Sap, Yanai Elazar
cs.AI
Humans know that airplanes are fast, that this extends to red airplanes, but that it does not hold for broken airplanes. How do LLMs acquire category knowledge that humans learn and apply effortlessly? We introduce LeCat, a two-part framework to analyze LLM's Learning of Category knowledge. First, we use LeCat to evaluate models on their ability to learn category knowledge, distinguishing between three cases: memorization of in-domain...
-
10
Smart Home Agents Make Capable but Unpredictable Grid Operators
Christopher Terrazas, Eduardo Cotilla-Sanchez
cs.AI · cs.MA
AI-enabled smart homes are becoming more common across the grid edge. However, there has not been much work on failure response. This area is critical because smart homes operate on the grid edge where failures can cascade down. If a power outage happens within a smart home, a user has to manually troubleshoot their smart home to include tasks such as power load balance and device recovery. We conduct the first resilience analysis of smart...
-
11
VelServe: Taming Decode Jitters in LLM Inference with Tail-Calibrated Scheduling
Ishaan Datta, Alind Khare, Koushik Kumar Dey, Ratnesh Jamidar, Anand Kumar Singh
cs.AI
Interactive LLM services must meet latency service-level objectives (SLOs) for the time to first token (TTFT) and the time between tokens (TBT), as streaming and soft real-time applications require predictable token delivery. We identify decode jitters in both aggregated and disaggregated serving. A jitter delays every request in the batch, and long responses span hundreds of steps, so even rare overruns cause many SLO violations. In...
-
12
VLAN: Vision-Language Accessible Navigation
Jie Hu, Yu Zheng, Wenzhi Wu, Weixing Feng, Cunlei Cheng, Jiaming Zhang
cs.AI · cs.CV
Accessible mobility is user-conditioned rather than scene-intrinsic, as walkable paths for one embodiment are inaccessible to another. Yet, existing benchmarks evaluate traversability under a fixed and limited embodiment. We present Vision-Language Accessible Navigation (VLAN), containing 1,000 scenes, 20K navigation trajectories, and 160K keyframes across diverse lighting, environmental conditions, scene semantics, and path geometries. For...
-
13
Causal AI-Driven Secure mmWave Beam Alignment with Defensive Variational Autoencoders
Nasir Khan, Asmaa Abdallah, Abdulkadir Celik, Ahmed M. Eltawil, Sinem Coleri, Cicek Cavdar
cs.AI
Efficient and secure beam alignment is essential for mmWave communication systems. However, existing deep learning (DL)-based beam alignment methods often neglect causal relationships between inputs and outputs, resulting in limited interpretability, poor generalization, and excessive beam sweeping. Moreover, these DL solutions are vulnerable to adversarial attacks, where small perturbations in received power measurements can mislead beam...
-
14
Experts Across Schemas: Agent-Guided Mixture-of-Relational-Experts for Cross-Database Generalization
Hiren Madhu, Sukanta Ganguly, Kiran Srinivasan, Smita Krishnaswamy, Rex Ying
cs.AI
Web platforms record user and item activity in relational databases whose schemas differ from platform to platform, which makes it difficult to transfer predictive models between them. Relational foundation models address this through cross-database pretraining, yet recent improvements have relied on increasingly large pretraining corpora. We ask whether a better architecture, together with features specific to the target database, can...
-
15
When evaluation becomes intervention in clinical AI
Anthony Abou Mrad, Aviona Conti, Samuel Schmidgall, Jayanth Pratap, Ruhika Iyer, Joseph Kim, King Shi, Yann Sakref,...
cs.AI · cs.CL · cs.CY
AI judges, models that grade another system's output against a rubric, extend clinical review to the scale at which clinical AI writes. When teams use judge assessments to select a prompt or train a model, the judge becomes part of the intervention. Selection can then favor errors the judge overlooks. We describe what a judge's report must contain and the independent clinical test each judge-driven change needs.
-
16
Dancing Tokens on the Vocabulary Network from LLM Generation
Yuan-Chao Hu
cs.AI · cond-mat.dis-nn
Large language models (LLMs) generate text one token at a time, yet how a particular generation relates to the geometry learned in pre-training remains unclear. The fundamental explainability of LLMs is elusive. Here, we build a similarity network from the input embeddings of six open LLMs and map generation onto it. The token-embedding network is scale-free while heavy-tailed, as are random embeddings with matched covariance, but far more...
-
17
Probabilities of Causation in Nondeterministic Causal Models
David S. Watson, Sander Beckers
cs.AI
We study probabilities of causation in nondeterministic causal models, where mechanisms may remain intrinsically stochastic even after all latent variables are fixed. Focusing on binary treatments and outcomes, we develop a generic identification program that represents observational and interventional data as moment constraints on latent stochastic mechanism types and computes minimal/maximal values of counterfactual quantities via...
-
18
Large Language Model-Empowered Intelligent Agent for Adaptive Fast-Charging Control of Lithium-Ion Batteries
Joey Chan, Haoyu Pan, Zhen Chen, ErShun Pan
cs.AI
Fast charging of lithium-ion batteries is a multi-objective control problem that requires reducing charging time and sustaining high energy throughput while suppressing accelerated degradation and safety-critical electrochemical reactions. Conventional protocols are easy to implement but have limited ability to adapt to variations in battery chemistry, operating conditions, and aging state. Model-based optimization and conventional...
-
19
JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Exams
Issa Sugiura, Taro Makino, Takashi Ishida
cs.AI
Large language models (LLMs) are increasingly applied to finance, creating a need for benchmarks that evaluate their capabilities across financial systems with different regulations and practices. However, existing financial benchmarks provide limited coverage of country-specific financial systems, and they are difficult to keep up to date as released questions leak into training data. We introduce JFinBench, a Japanese financial benchmark...
-
20
Optimizing Drilling Trajectories in Multi-Material Structures Using Quantum Annealers
Eneko Osaba, Antonio Rubio-Mateos
cs.AI · cs.ET
In this work we present a quantum-hybrid optimization approach for planning drilling trajectories on multi-material structures, with the objective of minimizing total energy consumption. The proposed formulation models the drilling process as a constrained routing problem in which each hole must be visited while accounting for heterogeneous material properties, material-dependent drilling costs and displacement energy, as well as tool-wear...
-
21
Do Machines Learn Deviance From Their Peers? A Randomized Test of Differential Association With AI Agents
Murat Ozer, Arif Akgul, Amitabh Chakravorty
cs.AI
Differential association theory and its extension, social learning theory, hold that rule-breaking, and the definitions that make it acceptable, are learned through interaction with others. Because people choose their friends, this claim has been hard to test. We addressed this selection problem with AI agents, which learn only through communication and can be assigned to peers at random. In a preregistered experiment, 420 teams of three...
-
22
Two-Clustering Regime of Token Dynamics in Causal Attention
Trinh T. Nguyen, Duy-Tung Pham, Hoang-Son Do, Tan Minh Nguyen, Thieu N. Vo
cs.AI
We partially resolve Conjecture 1 of [Karagodin et al., Clustering in Causal Attention Masking (NeurIPS 2024)] and extend it to time-dependent parameter regimes. The conjecture predicts that causal attention dynamics converge to two clusters aligned with the eigenvectors associated with the largest eigenvalue $λ_{\max}$ of the value transformation. We prove that this behavior holds when $λ_{\max}>0$ and is generally false when $λ_{\max}\le0$....
-
23
A$^3$: Adaptive Audio Agent Framework for Collaborative Edge Computing
Zexin Li, Xueyi Zhang, Tao Ren, Yiming Chen
cs.AI
Embedded audio agents need a nearby edge server for speed, but a server-dependent agent returns nothing when the link fails. We present A$^3$, an adaptive audio agent framework that places whole pipeline stages on the server, keeps a complete fallback agent on devices that can host one, and hedges both paths with a link-aware deadline that decides when to give up on the server. On Jetson devices and an RTX A4500 server, A$^3$ matches the...
-
24
Understanding the limits of snapshot-based fault diagnosis in distribution networks
Ba Tu Phung, Huy Hoang Le, Kim-Anh Nguyen
cs.AI
Inverter-based resources weaken fault currents in distribution networks, and snapshot-based diagnosis, which classifies a fault from voltage phasors at a few buses at one instant, offers a cheap first-stage screen. Its published accuracies, however, rest on different noise assumptions and do not show whether the error comes from the classifier, the features, the measurement error, or the fault resistance. This paper separates these sources on...
-
25
LACCO: Local Accumulation with Computation--Communication Overlap
Daniele Kopyshevskiy, Benjamin Th{é}rien, Nicolas Pinto, Edouard Oyallon
cs.AI · cs.LG
Training language models across low-bandwidth networks requires reducing synchronization overhead. Local optimization methods such as DiLoCo communicate only after several local steps, but outer gradient averaging and the outer update remain on the critical path. Existing computation-communication overlap methods avoid this stall through delayed or replica-local updates, which can degrade convergence or cause replicas to drift. We propose...
-
26
Interactive deep-learning based interface for brain tumour segmentation
Enora Giffard, Pierre Jannin, John S H Baxter
cs.AI
Brain tumour segmentation from MR images is an integral part of their treatment, either through surgical resection or radiotherapy. Both applications require a high degree of precision that can be difficult to ensure for all patients due to the high degree of variability in the size, shape, number, and location of these tumours. This leads to difficulties with their automatic segmentation via deep learning, which can display catastrophic...
-
27
TotalSegmentator Aorta Report: Automated Aortic Diameter Measurement at 11 Standardized Landmarks on CT Images
Jakob Wasserthal, Daniel Hinck, Martin Segeroth, Joshy Cyriac, Denis Berdajs, Jules Miazza, Maurice Pradella
cs.AI
Purpose: To develop and evaluate a fully automated, open-source tool that measures aortic diameters at 11 standardized landmarks from the aortic annulus to the bifurcation on any CT image, following current guideline recommendations. Materials and Methods: This retrospective single-center study included 239 arterial phase CT angiography examinations of 230 patients (median age, 65 years [range, 18-99 years]; 163 men) performed between April...
-
28
WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents
Imene Kerboua, Fatemeh Pesaran Zadeh, Xing Han Lù, Weijian Qi, Alexander Miller, Junyi Song, Yunjia Tian, Dongjin...
cs.AI · cs.CL · cs.LG
Web agents powered by large language and vision-language models are increasingly applied to realistic browser work that spans heterogeneous applications, multimodal content, and stateful workflows. However, existing reproducible web-agent benchmarks cover only a small number of web applications drawn from a few software categories, and restrict modality to text and vision. Live benchmarks broaden site coverage but sacrifice reproducibility,...
-
29
The Transformer Paradigm: Dynamic Processing and a New Principle of Inference
Marco Giunti, Fabrizia Giulia Garavaglia
cs.AI · cs.AR · cs.CY · cs.ET · cs.NE
We argue that the Transformer revolution is not adequately understood as a merely quantitative expansion of deep learning, but as the emergence of a new paradigm based on a different principle of inference. We interpret the Transformer as a system in which token representations are transformed by parameterized transformations, or transforming concepts. During inference, some of these transformations are dynamically constructed from the...
-
30
Toward Interference-Agnostic RF Source Separation
Maxence Albert, Raphaël Duroselle, Thibaud Ehret, Olivier Boeffard, Jean-François Bonastre
cs.AI · eess.SP
Separating a radio-frequency signal of interest from a co-channel interference is mostly addressed with specialized separators, each trained for one pair of signal and interference types and therefore relying on a label that a heavily jammed receiver cannot identify. We show that this reliance is not benign: applied to an interference it was not trained on, such a separator usually fails to recover the signal, and in most of the cases we...
-
31
Measured from the feed: the unsustainable growth of AI video generation
Tristan Coignion, Aurélie Bugeau, Gael Guennebaud, Anne-Laure Ligozat
cs.AI · cs.CV · cs.CY · cs.ET
Text-to-video generation runs at commercial scale, but its broader environmental impacts remain, to our knowledge, understudied. Providers rarely disclose video volumes or energy needs; we measured the yearly video output of two commercial platforms and built a prospective model of such services' absolute footprint from training to storage. Our projections suggest that reducing emissions depends on both limiting growth in video generation and...
-
32
Tracing Actual Causes with Counterfactual Witness Maps
Tim Woydt, Matej Zečević, Kristian Kersting, Moritz Willig
cs.AI · cs.LO
Halpernian actual causation, the formal study of which events in a specific situation caused a specific outcome in acyclic structural causal models, underpins legal responsibility, moral blame, and the assessment of causal harm. Despite the rich logical framework, no prior sound and complete enumeration procedure is known for finding all actual causes in a given setting, blocking downstream tasks such as responsibility attribution, blame...
-
33
OutfitterBench: Evaluating LLM Agents on Long-Horizon Resource Allocation and Commitment Coordination
Jie Huang, Yuecheng Hong, Yao Chen, Shengding Jiao, Xudong Liu, Qiang Ye
cs.AI
In many long-horizon settings, an agent's own choices create future constraints: committing finite capacity establishes future obligations and forecloses later opportunities. Sustaining performance therefore requires both keeping evolving plans feasible and comparing the value of resource allocations with the alternatives they displace. Recent benchmarks increasingly evaluate LLM agents in continuing operations, but give less attention to how...
-
34
Evaluating Large Language Models for Scientific Paper Search: Retrieval Success and Inference Latency on Mac Studio and NVIDIA A100
Frederic Andriantseheno Rakoto, Yannis Bendi-Ouis, Xavier Hinaut
cs.AI
Scientific literature search can benefit from locally deployed LLM assistants, which reduce reliance on hosted model providers while giving research teams greater control over their data and infrastructure. This work investigates whether open-weight models can support web-assisted paper retrieval under practical computing constraints. We first characterize inference latency as the input context grows from 512 to 128k tokens on a Mac Studio...
-
35
What Balanced Accuracy Cannot Identify in Neural-Signal Decoding under Test-Time Adaptation
Jiangshuo Xie, Zonghan Wu
cs.AI
Adaptation for neural-signal classification is usually transductive: each batch is scored after updating on it, and the gain depends on the adapted model [4]. This paper asks what an aggregate change fails to characterise inside the cohort. Full test-time adaptation (full_ttt) was evaluated in 11 dataset-encoder cells (four each on Siena/EEG and PTB-XL/ECG, three on Sleep-EDF/EEG), with splits and source-model evaluation fixed; the subject...
-
36
RecMem: Recurrent Memory Compression for Long-Sequence Generative Recommendation
Haoyi Hu, Gaoyang Guo, Yunjia Xi, Wen Chen, Weiwen Liu, Jian Wu, Yuning Jiang, Weinan Zhang
cs.AI · cs.IR
Generative recommendation benefits from long interaction histories, but the cost of processing them directly grows with history length. We propose RecMem, a recurrent memory compression framework guided by three desiderata: space invariance, semantic fidelity, and lifelong evolvability. RecMem compresses historical segments into a fixed set of memory slots using a bifurcated encoder-decoder with shared lower layers and slot-wise forget-gated...
-
37
When Cooperation Must Change: Semantic Strategy Unlearning in Multi-Agent Reinforcement Learning
Wenhan Wu, Linghan Chen, Yudong Gao, Fan Yang, Honglong Chen, Kai Yin, Jiawei Jiang, Chuang Hu
cs.AI
Cooperative multi-agent reinforcement learning (MARL) supports coordinated decision-making in distributed Web services, multi-robot control, and collaborative games through learned coordination conventions. When deployment requirements change, a previously useful convention may become obsolete or unsafe. For example, revised cache-sharing permissions in Web content delivery may require caches to abandon a learned division of storage and...
-
38
SWIFT: Sample-Wise Instance Fine-Tuning of Time-Series Foundation Models for Forecasting
Yang Chen, Feifan Tian, Cong Wang, Cheng Feng, Wenbin Li, Yang Gao
cs.AI
While current few-shot adaptation strategies for time series forecasting foundation models are predominantly dataset-centric, the necessity of obtaining an additional dataset for the finetuning process poses a significant hurdle for adoption. To address this constraint, we propose Sample-Wise Instance Fine-Tuning (SWIFT), a novel forecasting adaptation framework that achieves fine-grained specialization by leveraging structural priors from...
-
39
Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners
Stephen Obadinma, Xiaodan Zhu
cs.AI
As large language models (LLMs) are increasingly deployed as autonomous agents, their abilities in navigating automated planning tasks have become essential. However, despite their strengths, LLMs' planning ability is not robust, particularly when they are not allowed to exploit commonsense cues in the symbolic vocabulary (e.g., names of actions, predicates, and objects) used to define planning tasks. This makes LLMs unreliable compared to...
-
40
Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
Mike He, Ankush Desai, Sharad Malik, Aarti Gupta
cs.AI · cs.SE
LLM agents that execute multi-step tool calls must satisfy two objectives simultaneously: completing the user's task (utility) and conforming to domain policies and correctness constraints (safety). These objectives are in tension -- blocking an unsafe action prevents a violation but can leave the agent stranded with no principled way to recover. Existing approaches sacrifice one objective for the other. We introduce Soteria, a framework that...
-
41
OmniScore-Bench: Evaluating Vision-Language Models on Musical Score Reading
Congren Dai, Zhancheng Guo, Danni Zhao, Wenchu Wang, Xiaobing Li, Maosong Sun
cs.AI
Vision-language models (VLMs) can answer questions about musical scores, but their ability to recognise notation, recover its structure and interpret its musical meaning requires separate evaluation. Existing optical music recognition (OMR) resources establish detection and transcription measurements; a transcription score alone leaves the strengths and bottlenecks of a VLM score reader unresolved. We introduce OmniScore-Bench, an evaluation...
-
42
FlexCast: Flexible Context Learning for Time Series Foundation Models
Zuyang Shen, Luqi Gong, Fanda Fan, Bingsong Wang, Xiang Ao, Yahui Wei, Minghao Liu, Chunjie Luo, Jianfeng Zhan
cs.AI
Time series foundation models (TSFMs) based on autoregressive (AR) next-token prediction entangle two factors: variable-context conditioning and prediction-unit factorization with autoregressive rollout. Strong AR performance therefore does not reveal whether generalization stems from the flexible training distribution, the local prediction target, the left-to-right inference process, or their combination. We propose FlexCast, a flexible...
-
43
AI-aided Decision-Making in Education - Uncertainty, Explainability, and Human Responsibility
Fabian Kieser, Paul Tschisgale, Peter Wulff
cs.AI
As Artificial Intelligence (AI)-based systems have become increasingly integrated into various aspects of everyday life, including education, understanding how these systems make decisions is of paramount importance. AI holds significant potential to enhance educational practices through the facilitation of personalized and adaptive learning, automation of assessment procedures, and assistance with administrative tasks. However, the opacity...
-
44
DECODE: Diagnosing Interpretability Failures in Automated Interpretation Process
Dohyun Kim, Jaeung Lee, Donghee Hong, Jaemin Jo
cs.AI · cs.HC
Tools for interpreting the internal representations of Large Language Models (LLMs) increasingly rely on LLMs themselves to both generate and evaluate explanations, creating a self-referential automated interpretation process with minimal human oversight. This automation raises significant reliability concerns, which are exacerbated by the absence of ground truth. In practice, it is difficult to validate explanations or to attribute...
-
45
Is Abliteration Getting Harder? Not Uniformly: Refusal Removal by Direction-Based Ablation and ARA in Heretic on the Qwen3.8, Gemma 4, Olmo 3.1 and Mistral Small 3.2 LLMs Versus Their Predecessors
Richard J. Young
cs.AI · cs.CL
Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, which ablates a refusal direction, increasingly fails on newer models. On five release pairs, refusal removal did not become uniformly harder. Qwen2.5-32B and Qwen3.8-27B, Gemma-2-27B and Gemma-4-31B, OLMo-2-32B and...
-
46
Aligning AI Teams
Siddarth Srinivasan, Morgan Jane Matthews, Jascha Sohl-Dickstein, Erik Jones
cs.AI
Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two software-engineering tasks (sepsis triage, a news recommender) and ten consulting-proposal generation tasks. We present four findings: (1) The single-vs-team safety gap...
-
47
Causally Constrained and Uncertainty-Aware Cardiopulmonary Risk Prediction
Yuxiang Lai, Jiashuo Zhang, Liang Zhao, Xiaofeng Yang
cs.AI
Routine chest computed tomography (CT) captures pulmonary, cardiac, and vascular phenotypes that jointly stratify lung cancer and cardiovascular disease, the two leading causes of death in lung-screening populations. Yet clinical risk calculators evaluate each disease in isolation and omit CT findings, whereas unconstrained machine learning overfits small hospital cohorts, learns treatment- and illness-confounded risk directions, and conceals...
-
48
G-CAST: Governed Continual Self-Training for E-Commerce Agents under Evolving Demands
Yuechun Yu, Wenzheng Kong, Xiaofeng Mao, Jin Zhang
cs.AI · cs.CL
With the rapid advancement of Large Language Models (LLMs), an increasing number of users are turning to LLM-powered agents for conversational shopping in e-commerce. However, the user needs continue to change as new product categories, procurement scenarios, and feature requests emerge. At the same time, the product's execution harness-including its tools, skills, and operating procedures-continues to evolve to support increasingly...
-
49
Can Agents Keep Up with Time? An Empirical Analysis of Temporal Adaptation After a Conversational Hiatus
Hongguan Su, Ming Wang, Shun Zhang, Yifan Wang, Rong Yin, Zhiming Ma, Mengzheng Yang, Peng Chen
cs.AI
Long-horizon agents increasingly serve as persistent personal assistants across modern web platforms, managing schedules, applications, and multi-step plans over weeks or months. Users often return to an ongoing conversation after a long conversational hiatus, while earlier bookings and preparation notes stay on record. During this hiatus, scheduled dates may pass even though the retained records remain unchanged and event outcomes go...
-
50
Vision-as-a-Tool: Visual Harness for Multimodal Agentic Coding
Haolin Yang, Wenshan Wu, Jin Jiang, Yu Cheng, Yan Xia, Ting Song, Yangyu Huang, Zhiliang Peng, Wenhui Wang, Hangbo...
cs.AI · cs.CV
Multimodal agentic coding requires robust visual reasoning to analyze observations and evaluate generated artifacts. Current frameworks largely rely on a Thinking-with-Images paradigm, where agents depend on their intrinsic vision to execute visually grounded tasks. However, this architectural coupling introduces a fundamental bottleneck. Agent performance remains strictly bounded by internal perceptual limitations. Furthermore, text-only...
-
51
Robustness Evaluation of GPU Cloud Pricing Benchmarks under Incomplete Observations: A Controlled Missingness Study
Jooya Wong
cs.AI
Daily GPU rental-price benchmarks can fail when marketplace quotes are missing. This article stress-tests a fixed equal-weight median rule under four imposed masking mechanisms and four benchmark-level recovery methods. Across 5,800 Monte Carlo realisations in 27 scenarios on 190 held-out days, whole-source outages reduce publication coverage to 0.77 while preserving zero conditional error on published dates; composition-changing loss retains...
-
52
MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals
Jiwon Jeon, Myungsik Cho, Woojun Kim, Seongmin Kim, Woohyeon Byeon, Seungyul Han, Youngchul Sung
cs.AI
The performance of offline Multi-Agent Reinforcement Learning (MARL) is limited by the quality of the fixed offline dataset, motivating trajectory augmentation. However, augmenting multi-agent trajectories presents a fundamental challenge of the diversity-coordination trade-off: independent generation improves diversity but lacks coordination, while joint generation induces coordination but lacks diversity, reproducing the training...
-
53
AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning
Simon Tang, Wenjie Shi, Yongjing Yin, Keheng Wang, Jialin Liu, Zheng Zhang, Linvo Lin, Xiangyuan Xue, Kan Ren,...
cs.AI · cs.LG
Recursive self-improvement (RSI) is one of the most promising paths toward an AI singularity for superintelligence. Achieving this vision requires AI systems to undertake the full training pipeline for iterative improvement. Reinforcement learning (RL) plays an essential role in this cycle to improve model capabilities and generalization, yet automating RL remains difficult due to unstable training dynamics and the need for sustained...
-
54
TReC: Evaluating Move-Induced State Changes in Instruction-Conditioned Go
Zhuangsheng Li, Yunhan Zhang, Dailin Li, Qingxian Yu, Yu Wu, Youqi Song, Bangyuan He
cs.AI
When a Go model predicts a move different from the expert's, coordinate distance measures how far the prediction lands from the reference. We introduce Transition Representation Consistency (TReC) to compare how the two moves change a board-state embedding. Both moves are executed from the same position under the game rules, and TReC is the cosine similarity between the two resulting representation changes. In experiments with a frozen KataGo...
-
55
Certified Improvements to Best-Known Thomson-Problem Configurations with a Search Pipeline Built with Large Language Model Agents
Hui Shao, Tao Wang, Xiaotian Liu, Yijie Peng
cs.AI
The Thomson problem asks for N unit charges on a sphere with minimum Coulomb energy; for large N the best configurations known are curated in the Cambridge Cluster Database, whose largest-N entries were set in October 2026. We report configurations for N = 912, 1382 and 2502 with energies 0.0036186, 0.0109730 and 0.0614033 below the database values, certified by exact integer arithmetic. All three are numerically strict local minima modulo...
-
56
Knowledge After Collapse: Context and Wording Shape Factual Accessibility in Language Models
Sujato Dutta, Prithviraj Patil, Chandrajit Bajaj
cs.AI
When a language model accepts a false correction in a factual discussion, its next answer can depend on how the conversation continues. We introduce Knowledge Answer Divergence (KAD), an event-conditioned evaluation protocol that distinguishes initial false-answer adoption from subsequent persistence, recovery, and abstention. KAD freezes the conversation at the first explicit adoption of a designated false target and branches independent...
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.