English
Related papers

Related papers: TAME: A Trustworthy Test-Time Evolution of Agent M…

200 papers

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…

Artificial Intelligence · Computer Science 2026-05-12 Ye Yu , Xiaopeng Yuan , Haibo Jin , Heming Liu , Yaoning Yu , Haohan Wang

Large Language Models (LLMs) are increasingly used as autonomous agents for multi-step tasks. However, most existing frameworks fail to maintain a structured understanding of the task state, often relying on linear prompt concatenation or…

Artificial Intelligence · Computer Science 2025-08-26 Ye Ye

Large Language Model (LLM) agents are increasingly deployed to automate complex workflows in mobile and desktop environments. However, current model-centric agent architectures struggle to self-evolve post-deployment: improving…

Artificial Intelligence · Computer Science 2025-12-19 Zibin Liu , Cheng Zhang , Xi Zhao , Yunfei Feng , Bingyu Bai , Dahu Feng , Erhu Feng , Yubin Xia , Haibo Chen

Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-horizon tasks and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Han Xiao , Guozhi Wang , Hao Wang , Shilong Liu , Yuxiang Chai , Yue Pan , Yufeng Zhou , Xiaoxin Chen , Yafei Wen , Hongsheng Li

Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. However, existing designs almost exclusively adopt a centralized…

Multiagent Systems · Computer Science 2026-05-22 Guangya Hao , Yunbo Long , Zhuokai Zhao

Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically optimize agent capabilities or communication topologies. However, existing methods…

Computation and Language · Computer Science 2026-05-12 Chen Xu , Yicheng Hu , Ruizi Wang , Xinyu Lin , Wenjie Wang , Dongrui Liu , Fuli Feng

Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. In this study, we investigate…

Computation and Language · Computer Science 2026-04-21 Weixiang Zhao , Yichen Zhang , Yingshuo Wang , Yang Deng , Yanyan Zhao , Xuda Zhi , Yongbo Huang , HaoHe , Wanxiang Che , Bing Qin , Ting Liu

As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models (typically written in SystemC) for early architecture exploration and verification. While…

Software Engineering · Computer Science 2026-04-28 Yifan Zhang , Jianmin Ye , Jiahao Yang , Xi Wang

Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iteration knowledge as natural-language feedback, flat episodic…

Artificial Intelligence · Computer Science 2026-05-12 Ruiyi Yang , Zechen Li , Hao Xue , Imran Razzak , Flora D. Salim

Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter…

Computation and Language · Computer Science 2023-08-08 Yang Luo , Xiaozhe Ren , Zangwei Zheng , Zhuo Jiang , Xin Jiang , Yang You

Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and leads to poor coverage of complex environment interactions. To address these challenges,…

Computation and Language · Computer Science 2026-04-20 Shidong Yang , Ziyu Ma , Tongwen Huang , Yiming Hu , Yong Wang , Xiangxiang Chu

Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…

Computation and Language · Computer Science 2024-09-12 Zora Zhiruo Wang , Jiayuan Mao , Daniel Fried , Graham Neubig

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the…

Artificial Intelligence · Computer Science 2026-05-28 Xujun Li , Kehan Zheng , Mingyuan Zhao , Yize Geng , Jinfeng Zhou , Qi Zhu , Fei Mi , Lifeng Shang , Minlie Huang , Hongning Wang

In this position paper, we address the persistent gap between rapidly growing AI capabilities and lagging safety progress. Existing paradigms divide into ``Make AI Safe'', which applies post-hoc alignment and guardrails but remains brittle…

Machine Learning · Computer Science 2025-09-09 Youbang Sun , Xiang Wang , Jie Fu , Chaochao Lu , Bowen Zhou

Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates…

With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolution stems from empowering LLMs with additional modules such…

Multiagent Systems · Computer Science 2025-03-14 Miao Yu , Fanci Meng , Xinyun Zhou , Shilong Wang , Junyuan Mao , Linsey Pang , Tianlong Chen , Kun Wang , Xinfeng Li , Yongfeng Zhang , Bo An , Qingsong Wen

The emergence of autonomous, high-velocity Agentic AI systems is creating an internal assurance scalability crisis. Point-in-time, document-based audits cannot keep pace with non deterministic behaviour and distributed deployments of agents…

Computers and Society · Computer Science 2026-03-05 Guy Lupo , Bao Quoc Vo , Natania Locke

Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance on static toolsets or offline training lags behind these dynamics, leaving…

Artificial Intelligence · Computer Science 2026-02-09 Haotian Li , Shijun Yang , Weizhen Qi , Silei Zhao , Rui Hua , Mingzhu Song , Xiaojian Yang , Chao Peng

Tool-using agent systems powered by large language models (LLMs) are increasingly deployed across web, app, operating-system, and transactional environments. Yet existing safety benchmarks still emphasize explicit risks, potentially…

Artificial Intelligence · Computer Science 2026-05-06 Zuoyu Zhang , Yancheng Zhu

The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal…

Software Engineering · Computer Science 2026-03-03 Guan-Yan Yang , Farn Wang