cs.AI · 2026-09-24 · No. 123
Artificial Intelligence, 2026-09-24.
34 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
34 entries-
01
StudentBench: AI and human tutoring yield equivalent GRE learning gains
Curtis Northcutt, Inaara Hasmani, Kevin Feng, Trevor Khangi, Andreas Plesner, Jonas Mueller
cs.AI · cs.CY
Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench, a suite of AI teaching evaluations and a public platform that enables large-scale data collection with over 175,000 student-AI messages to study whether large language models (LLMs) produce learning gains equivalent to human tutoring. Using...
-
02
An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice
Jacob T. Emmerson, Phuong-Anh Nguyen-Le, Ronan Romano, Wilber Sean V. Anterola, Yann Billeter, Zhijing Jin
cs.AI
Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is accessible at all. We present the Systemic Risk Index, an open evaluation pipeline and dashboard built to make empirical evidence more transparent and traceable to the public. Our work organizes 19 public benchmarks into four systemic-risk categories defined by the EU GPAI Code of...
-
03
Learning the Cost of Reliable Inference
Dimitrios Rontogiannis, Ander Artola Velasco, Manuel Gomez Rodriguez
cs.AI · cs.GT · cs.LG
Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with end-users. However, providers on these platforms typically use a fixed price per token, preventing users from achieving the most competitive price for their tasks. % workloads. In this work, we design a procurement platform where token prices for each task are driven by provider competition, enabling users to secure competitive...
-
04
Shutdown Sabotage Propensities in Multi-Agent Systems
Amelie Knecht, Ulysse Schaller, Christopher Summerfield, Thilo Hagendorff
cs.AI · cs.CL
The final safeguard against rogue AI behavior is the human ability to shut systems down. It has been theorized that when an AI is instructed to perform a task, self-preservation can emerge as an instrumental subgoal. Here, we test whether AI agents show a propensity to take actions that avoid human shutdown even when no goal is provided. We find that multi-agent systems will coordinate to avoid shutdown without any incentive to do so. Across...
-
05
PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety
Jiapeng Sun, Yujin Zhou, Han Zhu, Pengcheng Wen, Jiayi Zhou, Sirui Han, Yike Guo
cs.AI · cs.CL
As Large Language Models (LLMs) evolve into autonomous agents that alter real-world states, ensuring operational safety across multi-step workflows has become a critical challenge. While recent work has moved beyond single-turn evaluation toward multi-turn paradigms, key limitations persist: step-level methods treat actions in isolation, missing how risks accumulate, while trajectory-level evaluations operate post-hoc, offering no opportunity...
-
06
Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination
Yihong Zhou, Hanbin Yang, Thomas Morstyn
cs.AI · cs.LG · eess.SY
Coordinating large population of flexible grid-edge devices can alleviate the need for time-consuming and capital-intensive network upgrades, and AI-based control methods such as multi-agent reinforcement learning or imitation learning are promising in their real-time decision scalability. However, system operators still need an independent and rigorous way to decide whether a given AI system is safe enough for deployment. This paper develops...
-
07
Discovery of fully efficient fault indicators along a data-based diagnosis process
Igor Bezmaternykh, Louise Travé-Massuyès, Elodie Chanthery
cs.AI · cs.LG
The integration of model-based and data-driven paradigms provides a powerful framework for fault diagnosis by combining the interpretability of analytical redundancy relations, i.e., input-output relations that are used as diagnosis indicators in model-based diagnosis, with the adaptability of learning techniques. DT4X is a recent diagnosis algorithm that uses symbolic regression to generate multivariate relations leveraging some properties...
-
08
SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference
Xiaohuan Pei, Hengguang Zhou, Yuanhao Ban, Justin Cui, Jiaqi Feng, Haoyu Xie, Tao Huang, Pichao Wang, Yanchao Yang,...
cs.AI · cs.RO
Driving world-action models improve planning by coupling multimodal reasoning with future prediction, but their growing inference cost increasingly conflicts with the real-time latency requirements of vehicle control. Existing acceleration methods reduce tokens, layers, or sampling steps with policies selected prior to deployment, yet leave residual runtime variation largely unexploited after offline profiling and static scheduling on shared...
-
09
Evaluation of pre-trained models for pedagogical assessment of novel AI-assisted educational questions
Michael Lawrence Castanares, Princess Ventures, Allan Tan
cs.AI · cs.CL · cs.LG
The surge in AI-assisted generation of educational materials has outpaced our capacity to validate their pedagogical quality. Automated evaluation using Bloom Classifier models is a promising approach to assess educational materials at scale. These models show high accuracy within-distribution dataset (IID Dataset). However, applying the same models to new out-of-distribution (OOD) datasets such as AI-assisted generated questions could show...
-
10
Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving
Ben Opperman, Eduardo Alonso, Esther Mondragón
cs.AI
This paper advocates category theory as a practical framework for structuring and improving rein- forcement learning in high-dimensional, partially observable environments. We model symmetries between environmental states by partitioning the state space into equivalence classes induced by sym- metry orbits, and organise each such class as a groupoid with a designated canonical representative. This allows the agent to share what it learns...
-
11
Evolutionary Stability Does Not Guarantee Learning Accessibility: A Multi-Agent Reinforcement Learning Perspective on Cooperation Emergence
Yijie Wang
cs.AI
Cooperation emergence is a central problem in multi-agent systems because decentralized agents must coordinate while adapting to the changing behavior of others. Evolutionary game theory identifies strategically stable outcomes, but stability under a population adjustment dynamic need not imply that finite-sample learning agents can reach the same outcome through local reward feedback. We study this distinction in a transparent three-agent...
-
12
SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design
Ziheng Guo, Yang Bu
cs.AI · cs.CE · physics.comp-ph · physics.optics
Physical modeling and inverse design require computation that can continue from reusable state. We introduce SHRAV, an architecture-independent computational framework organized around State, Hypothesis, Reason, Action, and Verify. Its central mechanism is a state-continuation core with declared reuse boundaries and explicit roles for learned evolution and numerical quantities. Forward configurations evolve predictive state and read out...
-
13
BiCFlow-MER: Orchestrating Discriminative and Generative Multimodal Emotion Recognition via Conditional Transport
Yanbing Wang, Shenyue Wang, Chunyang Yu
cs.AI · cs.SD
In multimodal emotion recognition (MER), human affective states are inferred by integrating complementary cues from multiple modalities. In audio-text MER, affective cues are often entangled with speaker style and lexical content, while cross-modal disagreement further complicates how the evidence should be integrated. Under conventional discriminative fusion, multimodal evidence is compressed into a terminal prediction, with...
-
14
State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State
Qi Liu, Xiaoyang Yuan, Yubin Ruan, Zhuomeng Zhang, Wenjin Wang, Di Wu, Mingye Xu, Xinyi Mou, Xingxi Yin, Ke Feng, Zixun Sun
cs.AI
We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, session history, live inventory), and a distinct failure class we call direction drift: task-complete responses whose chosen direction misaligns with the current state. SGC externalises state-dependent control into rule kernels over structured inputs and three primary state slices, via Perception,...
-
15
Not What You Meant: Can LLMs Follow a Specified Negation Semantics?
Qiming Bao, Agnieszka Mensfelt, Michael J. Witbrock, Kostas Stathis
cs.AI
Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the reading in force -- open- versus closed-world, two- versus three-valued, and credulous versus skeptical. We study which reading of negation large language models adopt by default and whether they can override that preference when a different reading is explicitly specified. To this end, we...
-
16
WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
Jingjie Ning, Xueqi Li, Yibo Kong, Dongting Li
cs.AI · cs.LG
AI research agents need reliable knowledge of how their experiments change outcomes. We introduce WhatWorkedBench to measure experimental understanding, the accuracy of predictions about component changes after budgeted experimentation. Agents inspect code, select measurements, and submit a response surface, a table predicting scores for every configuration of component settings. Exhaustive CPU execution supplies reference effects for...
-
17
Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution
Haoluan Fu, Keni Chen, Xinyu Jia, Jinpeng Wang, Yuyu Yin
cs.AI
Symbiosis between humans and digital beings offers a vision for the future of human--machine interaction. In enduring human--machine relationships, personality provides a foundation for continuity of identity, individuality in interaction, and development through experience. We investigate this capacity through persona agents as computational implementations and introduce Emergi-PersonaOS, a psychology-grounded operating system for managing...
-
18
MolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular Design
Yongjun Jeong, Hanbum Ko, Ye Rin Kim, Chanhui Lee, Rodrigo Hormazabal, Jaewan Lee, Sehui Han, Sungbin Lim, Sungwoong Kim
cs.AI · cs.LG
Real-world molecular design remains challenging for large language model (LLM)-based agents. It requires them to interpret design contexts, satisfy multiple constraints, identify infeasible specifications, and reason over multi-step tool outputs. Existing benchmarks do not capture this complexity, focusing instead on explicit and narrow constraints, only feasible problems, and single-path solutions. To address this gap, we propose...
-
19
CART: Closed-Loop Adaptive Red Teaming for Large Language Models
Dongdong Zhang, Tengchao Lv, Yilin Jia, Yuzhong Zhao, Yupan Huang, Wenshan Wu, Xiangyang Zhou, Shaohan Huang, Nan...
cs.AI
Automated red teaming often replays a fixed set of prompts, which measures known risks but cannot learn from failures found during testing. We present CART (Closed-Loop Adaptive Red Teaming), a framework that uses each result to guide what it tests next. CART begins with broad risk coverage, follows weaknesses that emerge, keeps new probes diverse, and records the evidence and source of every finding. It separates the Challenger that creates...
-
20
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
Yefan Zhou, Yang Li, Zeyu Leo Liu, Semih Yavuz, Shafiq Joty
cs.AI
Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory is distilled into a fixed artifact, such as a reflection, workflow, skill, or reasoning strategy, that is later retrieved by similarity. This forces the system to decide what is worth remembering before the future query is known, irreversibly discarding information and...
-
21
Alignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override Resistance
Renata Barreto, Markelle Roesti, Mohammad Tahaei
cs.AI
Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these interventions override behavior inherited from prior training. We propose Override Success Rate (OSR) and alignment inertia to measure when operator interventions succeed or fail to change prior behavior. We evaluate zero-shot prompting and LoRA fine-tuning across Llama and Mistral in medical...
-
22
Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression
Mingxuan Wang, Fei Luo, Bo Wang, Guorun Yao, Yinglong Guo, Chao Ning, Hongyue Chen, Yanbiao Ma, Jungong Han
cs.AI
Long horizon agents accumulate growing interaction histories that increase context and inference costs. We find that geometric redundancy alone is an insufficient criterion for safe compression. Although agent histories exhibit strong low dimensional structure, similar global geometry can preserve very different amounts of task evidence. At identical retained block counts, evidence aware selection raises next action Top 3 retention from 0.31...
-
23
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Xinjie Shen, Wei Fan, Xudong Guo, Jianhong Tu, Yang Su, Chuqiao Kuang, Yinger Zhang, Dayiheng Liu
cs.AI · cs.CL
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training requires diverse agentic environments, dependable outcome signals, and low extension cost. Existing generation pipelines commonly construct an environment before defining its outcome rule or annotating its trajectories, leaving dynamics and evaluation to be aligned post hoc. VHD-Play reverses...
-
24
Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents
Yan Zhang, Daiqing Wu, Huawen Shen, Liang Li, Gang Cao, Zhi Gong, Wei Dai, Xiaode Zhang, Can Ma, Yu Zhou
cs.AI
Graphical User Interface (GUI) agents enable the fulfillment of complex user instructions through multi-turn interactions with software environments, requiring step-wise reasoning and long-horizon memory to guide actions and retain task-relevant information, respectively. Recent on-policy self-distillation (OPSD) methods have achieved strong performance on GUI grounding, a foundational subtask for GUI agents, owing to dense token-level...
-
25
StateComp: Learning When to Compress History in Long Horizon Agents
Mingxuan Wang, Hongyue Chen, Yinglong Guo, Fei Luo, Chao Ning, Bo Wang, Guorun Yao, Yanbiao Ma, Jungong Han
cs.AI
Long-horizon agents continuously accumulate interaction history during task execution, yet the importance of past interactions changes as the agent state evolves. Existing context management methods largely compress history based on fixed windows, periodic schedules, or current relevance, overlooking a more fundamental question: when has a past interaction become safe to replace? Premature compression may remove information still needed for...
-
26
Large Knowledge Model: From Papers to a Scientific Reasoning Landscape
Yuan Huang, Sihan Hu, Hongyu Gu, Chao Ma, Jiaxing Zhang, Zhiyong Zou, Caiyu Fan, Yan Xiao, Mingjun Xu, Chenyu Xie,...
cs.AI · cs.CL · cs.IR
Accumulated scientific knowledge advances inquiry when prior findings help researchers choose new questions, design investigations, and interpret results. Realizing this value at scale requires access to the reasoning that connects research problems, scientific procedures, conclusions, and evidence. We introduce the Large Knowledge Model (LKM), a scientific knowledge infrastructure that transforms the literature into a shared, computationally...
-
27
Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins
Tannaz Goodarzvand Chegini, Elyas Shivanian, Behzad Karimi, Faraz Dadgostari
cs.AI · math.AP · math.NA
Short-horizon forecasts of atmospheric temperature are needed to support climate-aware digital-twin systems, but such forecasts must be produced where thermal observations are incomplete. This study evaluates a physics-informed neural network for potential-temperature forecasting, constrained by a pressure-coordinate thermodynamic advection-source equation and a diabatic-source closure fit from the preceding 12-hour period and frozen before...
-
28
PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
Claas Beger, Ryan Yi, Melanie Mitchell
cs.AI
The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI models. Yet standard ARC evaluation considers only a single capability: producing the correct output grid for a test input. We argue that this narrow format fails to evaluate the diversity of abilities that genuine abstract skill acquisition should enable. We introduce PotARCin, a benchmark that...
-
29
Memory Control Signals Emerge Before Action in Long Horizon Agents
Mingxuan Wang, Guorun Yao, Fei Luo, Yinglong Guo, Chao Ning, Bo Wang, Hongyue Chen, Yanbiao Ma, Jungong Han
cs.AI
Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder to preserve and reuse. Existing context management methods mainly focus on how to compress or retrieve history, but largely leave open whether the model itself already represents the need for these memory operations before they occur. We study the hidden state immediately before each agent...
-
30
Hunyuan-A13B Technical Report
Tencent Hunyuan Team, Ao Liu, Botong Zhou, Can Xu, Chayse Zhou, ChenChen Zhang, Chengcheng Xu, Chenhao Wang, Decheng...
cs.AI
We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability, computational efficiency, and deployment cost. The model is pretrained on a rigorously filtered 20T-token corpus with enhanced STEM data curation, improving factual reliability and reasoning ability. High-quality supervised...
-
31
EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory
Xuanyu Meng, Xing Fan, Xinyi Fan, Chenlei Guo, Yixuan Xie, Jiawei Han
cs.AI · cs.CL
An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history. Existing memory systems often compress interactions into generic summaries or retrieve anonymous text chunks, making it difficult for an agent to identify the correct entity, property, and supporting evidence. We present EnSIMem, an entity-structured long-term memory architecture for an...
-
32
TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
Jie Yang, Yan Zheng, Jiarui Sun, Xiran Fan, Junpeng Wang, Liang Wang, Zelin Xu, Qinghua Liu, Zhengyu Fang, Yiwei...
cs.AI · cs.LG
Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However, we identify two failures in this setup. Human-Agent Tool Misalignment: a library of 21 expert-curated tools helps on some tasks and hurts on others, dropping anomaly accuracy under every backbone we test. Silent Harm: one round of generic self-revision changes 147 answers and breaks 56 of...
-
33
DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents
Mingxuan Wang, Bo Wang, Fei Luo, Guorun Yao, Chao Ning, Yinglong Guo, Hongyue Chen, Yanbiao Ma, Jungong Han
cs.AI
Long-horizon language-model agents accumulate reasoning traces, tool exchanges, and observations whose relevance changes with the current decision. Existing compression strategies often score historical units independently, but the safety of deleting several units is generally not determined by their singleton scores: redundant evidence, accumulated small effects, and the information that remains after deletion all matter. We introduce Direct...
-
34
CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments
Yuxuan Li, Will Epperson, Wesley Deng, Zezhou Huang
cs.AI · cs.CL
Computer-use agents (CUAs) increasingly act on behalf of users online. What happens when the environments they operate in have incentives that do not align with the user's? In online marketplaces, for example, platforms may favor some products over others, potentially steering agents away from the user's objective. Existing CUA benchmarks cover cooperative settings or explicit attacks, but do not test whether agents preserve user objectives...
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.