English
Related papers

Related papers: On-Policy Self-Evolution via Failure Trajectories …

200 papers

Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding errors over extended horizons. PIVOT (Plan-Inspect-eVOlve…

Artificial Intelligence · Computer Science 2026-05-13 Tuo Zhang , Alin-Ionut Popa , Yan Xu , Rui Song , Dimitrios Dimitriadis

Deploying language-model agents in production often requires substantial compute and human effort to tune prompts, parsers, validators, and other components of the agent pipeline. Self-evolution offers a promising alternative, but most…

Machine Learning · Computer Science 2026-05-25 Chen Ling , Pei Chen , Albert Guan , Jiaming Qu , Shayan Ali Akbar , Madhu Gopinathan , Erwin Cornejo

LLM agents are widely deployed in complex interactive tasks, yet privacy constraints often preclude centralized optimization and co-evolution across dynamic environments. Despite the demonstrated success of Federated Learning (FL) on static…

Machine Learning · Computer Science 2026-01-13 Xiang Chen , Yuling Shi , Qizhen Lan , Yuchao Qiu , Min Wang , Xiaodong Gu , Yanfu Yan

Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue…

Computation and Language · Computer Science 2026-04-29 Amir Saeidi , Venkatesh Mishra , Souradeep Mukhopadhyay , Gaowen Liu , Ali Payani , Jayanth Srinivasa , Chitta Baral

Safety post-training has been studied extensively in single-step "chat" settings where safety typically refers to refusing harmful requests. We study an "agentic" (i.e., multi-step, tool-use) setting where safety refers to harmful actions…

Machine Learning · Computer Science 2026-03-04 Benjamin Plaut

Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produce linguistically coherent but physically infeasible goals,…

Robotics · Computer Science 2026-03-03 Bingchuan Wei , Bingqi Huang , Jingheng Ma , Zeyu zhang , Sen Cui

Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, leaving reflection quality unknown, and it relies on agents' own episode runs, offering no…

Artificial Intelligence · Computer Science 2026-05-29 Jiahao Huang , Fei Cheng , Junfeng Jiang , Zefan Yu , Akiko Aizawa

Pre-trained Vision-Language-Action (VLA) models represent a major leap towards general-purpose robots, yet efficiently adapting them to novel, specific tasks in-situ remains a significant hurdle. While reinforcement learning (RL) is a…

Robotics · Computer Science 2026-04-10 Baicheng Li , Dong Wu , Zike Yan , Xinchen Liu , Lusong Li , Zecui Zeng , Hongbin Zha

Test-time evolution of agent memory serves as a pivotal paradigm for achieving AGI by bolstering complex reasoning through experience accumulation. However, even during benign task evolution, agent safety alignment remains vulnerable-a…

Artificial Intelligence · Computer Science 2026-02-04 Yu Cheng , Jiuan Zhou , Yongkang Hu , Yihang Chen , Huichi Zhou , Mingang Chen , Zhizhong Zhang , Kun Shao , Yuan Xie , Zhaoxia Yin

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

Recent advances in large language models (LLMs) and agent system designs have empowered agents with unprecedented levels of capability. However, existing agent benchmarks are showing a trend of rapid ceiling-hitting by newly developed…

Artificial Intelligence · Computer Science 2026-03-25 Dadi Guo , Tianyi Zhou , Dongrui Liu , Chen Qian , Qihan Ren , Shuai Shao , Zhiyuan Fan , Yi R. Fung , Kun Wang , Linfeng Zhang , Jing Shao

The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…

Software Engineering · Computer Science 2025-11-04 Oorja Majgaonkar , Zhiwei Fei , Xiang Li , Federica Sarro , He Ye

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Artificial Intelligence · Computer Science 2025-07-14 Zeyang Sha , Hanling Tian , Zhuoer Xu , Shiwen Cui , Changhua Meng , Weiqiang Wang

Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…

Software Engineering · Computer Science 2026-04-03 Tyler Slater

Large Language Models (LLMs) have become integral components in various autonomous agent systems. In this study, we present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to…

Computation and Language · Computer Science 2024-07-11 Yifan Song , Da Yin , Xiang Yue , Jie Huang , Sujian Li , Bill Yuchen Lin

Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging and safety-critical scenarios. However, existing scenario…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Xinyu Xia , Xingjun Ma , Yunfeng Hu , Ting Qu , Hong Chen , Xun Gong

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

Software Engineering · Computer Science 2026-05-11 Cheonsu Jeong , Younggun Shin

The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. Current alignment…

Computation and Language · Computer Science 2024-06-18 Ruijun Chen , Jiehao Liang , Shiping Gao , Fanqi Wan , Xiaojun Quan

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficult to tailor responses to diverse application needs. %As a…

Computation and Language · Computer Science 2026-02-09 Jianfeng Si , Lin Sun , Weihong Lin , Xiangzheng Zhang
‹ Prev 1 2 3 10 Next ›