cs.AI · 2026-07-30 · No. 69
Artificial Intelligence, 2026-07-30.
24 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
24 entries-
01
Can AI agents conduct open-ended AI research? Early evidence from two case studies
Peter Kirgis, Sayash Kapoor, Andrew Schwartz, Stephan Rabanser, David Africa, Konstantinos Voudouris, Viet Nguyen,...
cs.AI · cs.CY · cs.LG
Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is thin. Current evaluations either test agents on narrow, verifiable tasks, which excludes open-ended research, or submit AI-generated papers to blind peer review, which is overstretched, stochastic, and suffers from poor review quality. We introduce a third way to measure progress towards AI R\&D...
-
02
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
Peter Tisnikar, Maja Swieczkowska, Benteng Ma, Gerard Canal, Matteo Leonetti
cs.AI · cs.HC · cs.MA
Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents. Most current ad-hoc teamwork (AHT) approaches assume that agents will collaborate on a single, fixed task and that the partner's capabilities, their ability to successfully execute the desired action, are already known. In reality, a partner's true capabilities are often hidden, and human collaborators may act sub-optimally on tasks with multiple...
-
03
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
Jingbo Zhou, Yusai Zhao, Qi Bao, Jingjia Cao, Zhenghai Chen, Chang Gao, Kaiqi Guo, Muxin Guo, Mingxuan Li, Xinjiang...
cs.AI · cs.CL · cs.HC
Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite...
-
04
Linguistic Monoculture in LLM-Assisted Language Use
Suhas Thejaswi, Juhi Kulshreshta, Lutz Oettershagen
cs.AI · cs.CL · cs.GT
Writing and communication are increasingly mediated by large language models (LLMs) that are being used to draft, revise and polish text. Although such assistance can improve clarity and help authors meet institutional expectations, widespread reliance on shared models may reduce population-level variation in linguistic form, a phenomenon we refer to as linguistic monoculture. We develop a mathematical framework in which authors and LLMs are...
-
05
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Yiping Song, Jiaoyan Chen, Renate Schmidt, Hui Yang, Wen Zhang
cs.AI
Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The existing OM systems identify only one type of semantic correspondence and cannot simultaneously discover equivalence and subsumption mappings. In this paper, we introduce Hybrid Ontology Matching (HOM), a new OM task that unifies equivalence and subsumption discovery, and accordingly propose a Large Language Model (LLM)-based...
-
06
On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
Yongjian Guo, Wanlun Ma, Lingyu Shen, Xi Xiao, Sheng Wen
cs.AI · cs.CL · cs.CR · cs.LG
Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers can embed harmful behaviors into downstream corpora, creating models that retain professional skills while violating human values on demand. Existing safety-realignment defenses often fail in practice due to three key limitations: they frequently cause catastrophic forgetting of specialized...
-
07
Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data
Lingyang Zeng, Guangze Chen, Kaichen Yu, Zhicheng Pan, Siyang Weng, Zirui Hu, Xiangyun Du, Hailin He, Rong Zhang,...
cs.AI · cs.CL
Personalized agents are increasingly applied to assist users across a wide range of tasks. Effective personalized assistance requires not only retrieving explicit facts from past interactions stored in agent memory, but also inferring abstract personal characteristics. However, existing memory benchmarks primarily evaluate whether an agent can retrieve information explicitly stated in conversational histories, failing to provide an effective...
-
08
Belief-Guided Decision Making with Uncertainty Gating in the Game of Go
Mehrad Yaghoubi, Azam Bastanfard, Abbas Jalilvand, Ashkan Rezaei
cs.AI
Recent advancements in Computer Go, driven by AlphaZero and MuZero, rely heavily on Monte Carlo Tree Search (MCTS) to correct the errors of the neural network policy. While effective on massive computational clusters, this dependence creates a critical bottleneck on consumer-grade hardware, where the computational cost of tree management severely limits inference rates. Furthermore, without deep search, these models suffer from hallucination,...
-
09
What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation
Vishisht Choudhary, Lukas Schmidt, Anne Zoë Kenntner, Feras Skhab, Michel Osswald, Jens Ernstberger
cs.AI · cs.CR
Bot detectors deployed at scale treat traffic as binary: human or bot. This assumption breaks when AI agents browse the web through browser automation, a traffic class that is neither and that binary classifiers structurally cannot represent. We present a three-class detection framework distinguishing humans, bots, and AI agents, and show that the binary-vs-agent confusion is architectural: a binary human-vs-bot detector misroutes agent...
-
10
From Passive Video to Editable Experience: Physically Grounded Experience Synthesis for Embodied Intelligence
Jia Luo
cs.AI · cs.RO
The key bottleneck in embodied AI is not model architecture but data. Although billions of human manipulation videos exist online, robots cannot directly learn from them due to the embodiment gap between human morphology and robot hardware. We introduce Pegasus, a low-resource framework that bridges this gap by translating human demonstrations into robot-learnable data through structured knowledge transfer. Instead of relying on raw video...
-
11
Property-driven Causal Abstractions for Markov Decision Processes
Jule Schmidt, Maximilian Weininger, Clemens Dubslaff, David Parker, Nils Jansen
cs.AI · cs.LO
Markov Decision Processes (MDPs) are widely used as decision-making models, commonly specified over factored state spaces through state variables and their valuations. The exponential blowup in the number of states renders many reasoning tasks in MDPs challenging. Abstractions are promising techniques to reduce MDPs and thus mitigate scalability issues. In this work, we introduce a notion of causality on factored MDPs and a novel...
-
12
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Huixiang Zhang, Mahzabeen Emu
cs.AI
Latent communication in large language model (LLM)-based multi-agent systems (MAS) transmits continuous internal representations instead of text, but greater representational capacity does not establish that the receiver uses task-relevant information. End-task performance alone also cannot reveal whether an observed effect depends on message presence, content generated for the evaluated example, or information supplied by a separate agent....
-
13
UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
Zhilun Zhou, Jianghao Yu, Yuming Lin, yongjun yang, Sun Yongquan, Depeng Jin, Yong Li
cs.AI
Large language model (LLM) agents have been widely applied in automating data science tasks. However, existing methods typically rely on a limited set of provided datasets, and they face challenges in data-intensive scenarios that require discovering and leveraging relevant information from large-scale and heterogeneous data repositories. Urban tasks are representative examples of such scenarios, as urban data are not only large-scale and...
-
14
AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
Junhao Qiu, Zidong Wang, Yansong Sun, Zhitong Ma, Ping Guo, Qingfu Zhang
cs.AI
Ascend C operator optimization is critical for NPU (Neural Processing Unit) inference performance but requires deep hardware expertise.While large language models (LLMs) have shown promise in automated CUDA kernel generation, the fundamentally different programming model of Ascend C introduces unique challenges that remain unexplored. In this paper, we propose AgenticCANN, a knowledge-augmented agentic evolution framework specifically...
-
15
Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting
Hongqiang Lin, Chao Liu, Xiaofan Bai, Xuan Jin, Yuhong Li, Nenggan Zheng, Xipeng Cao
cs.AI · cs.LG
Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applications. A promising solution is to treat skills as trainable states and optimize them in the same way as model parameters in neural network training. However, data-driven skill optimization is prone to overfitting to the limited trajectories collected from real environments. Overexploiting these...
-
16
AlphaSchema: Exploring the Space of Trading Semantics for LLM-Based Alpha Mining
Jingyang Yi, Jian Yang, Yifei Jin, Yuqi Li, Jian Li
cs.AI
Automated alpha mining has increasingly adopted large language model (LLM) agents for factor generation and iterative discovery. However, existing LLM-based systems often delegate both factor construction and search decisions to the agent itself, without an explicit exploration space or a principled mechanism for navigating that space. As a result, exploration remains largely implicit and difficult to control or optimize systematically. We...
-
17
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants
Zijian Xu, Wenshuo Zhang, Zisen Qin, Rui Sheng, Yushi Sun, Huamin Qu, Chuhan Shi
cs.AI · cs.HC
AI-assisted coding increasingly translates informal user intent into executable software, yet coding requests often contain ambiguities that recur in user-specific ways across tasks and sessions. Existing disambiguation methods typically address each ambiguous request in isolation within the current coding session, often through eliciting additional clarification. However, whether resolved session history from the same user can serve as...
-
18
Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models
Shaopeng Wei, Yufei Cheng, Wenxi Sun, Yepeng Ding, Yu Zhao, Gang Kou
cs.AI
The rapid development of large language models (LLMs) has renewed interest in agent-based modeling (ABM). However, current LLM-based ABM research faces several key challenges: modeling evolving agent-environment interactions, enabling flexible counterfactual reasoning, and automating simulation workflows for scientific research. In this paper, we propose Eco3S, a socio-economic system simulation framework for economic research and policy...
-
19
Evidence-Ledger Adjudication for Claim-Evidence Traceability
Gengyu Chen, Yongjie Yu, Weiling Wang
cs.AI
AI agents can draft claims faster than authors can check whether the cited or retrieved evidence supports them. We study evidence-ledger adjudication: a claim-evidence traceability workflow that pairs each claim with an evidence packet, assigns a support relation, and routes unsupported, contradicted, or mixed-evidence claims back to the author. The empirical core is a 2,335-row blind benchmark built from independent external labels in...
-
20
EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
Peng Yin, Kai Li, Yifan Zhang, Jian Cheng
cs.AI · cs.LG · cs.NE
Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural representations, loss formulations, and optimization dynamics. While Large Language Models (LLMs) offer a promising avenue for automated design, unconstrained code generation often yields mathematically invalid or numerically...
-
21
MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning
Kawai Chung, Chunkit Chan, Yauwai Yim, Yuxuan Liu, Haochen Shi, Weiqi Wang, Qing Zong, Tianshi Zheng, Yixuan Fu, Kai...
cs.AI
Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning remains insufficiently studied. Existing evaluations predominantly examine static text or isolated visual snapshots, which do not reflect the cumulative nature of real-world behavioral drivers. To address this gap, we introduce MultivationBench, a benchmark...
-
22
CG-World: A Large-Scale World-State Dataset and Protocol for World Models
Yiming Cai, Fangjie Yu, Meiqing Yu, Ziyue Shi, Pengfei Yuan, Yong Guo
cs.AI · cs.CV · cs.GR
World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually capture only part of this structure. We introduce CG-World, a large-scale world-state dataset and protocol derived from industrial computer graphics production pipelines. CG-World explicitly records intermediate states, including multimodal semantics, spatial structure, skeletal and controller...
-
23
CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games
Zheng Zhang, Nanjie Yao, Jiarui He, Deheng Ye, Peilin Zhao, Hao Wang
cs.AI
Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents. These games require complex social skills such as reasoning, deception, and collaboration. While recent advances in large language models (LLMs) have driven significant progress in SDG agents, current approaches are predominantly text-based, overlooking the multimodal nature that is fundamental to human social interaction. To bridge this gap, we...
-
24
Exploring Structures in Physics Problems: Can AI Agents Discover Statistical Mechanical Mappings?
Wanyu Zhao, Wanbing Zhao
cs.AI
An important skill in theoretical physics is to recognize when a new problem can be transformed into a known model. We study this skill as an AI-agent task: can LLM-based agents discover statistical mechanical mappings from a raw partition function to a tractable representation? To probe this question, we introduce StatMechBench-v0, a benchmark of six Ising-type problems covering transfer-matrix methods, gauge-removable disorder, and...
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.