中文
相关论文

相关论文: Meta-Cognitive Memory Policy Optimization for Long…

200 篇论文

Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant…

人工智能 · 计算机科学 2026-04-10 Ruoran Li , Xinghua Zhang , Haiyang Yu , Shitong Duan , Xiang Li , Wenxin Xiang , Chonghua Liao , Xudong Guo , Yongbin Li , Jinli Suo

Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing approaches often suffer from planning hallucinations and require…

计算与语言 · 计算机科学 2025-09-11 Weimin Xiong , Yifan Song , Qingxiu Dong , Bingchan Zhao , Feifan Song , Xun Wang , Sujian Li

Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the discovery of novel states. We propose…

机器学习 · 计算机科学 2026-03-09 Zeyuan Liu , Jeonghye Kim , Xufang Luo , Dongsheng Li , Yuqing Yang

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments…

机器学习 · 计算机科学 2026-05-22 Sikuan Yan , Ahmed Bahloul , Ercong Nie , Susanna Schwarzmann , Riccardo Trivisonno , Volker Tresp , Yunpu Ma

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Dawei Yan , Haokui Zhang , Guangda Huzhang , Yang Li , Yibo Wang , Qing-Guo Chen , Zhao Xu , Weihua Luo , Ying Li , Wei Dong , Chunhua Shen

Multi-agent systems of large language models (LLMs) show promise for complex reasoning, but their effectiveness is often limited by fixed collaboration protocols. These frameworks typically focus on macro-level orchestration while…

人工智能 · 计算机科学 2025-12-10 Wei Yang , Jesse Thomason

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working…

计算与语言 · 计算机科学 2026-03-05 Zhenting Wang , Huancheng Chen , Jiayun Wang , Wei Wei

Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge acquisition, reasoning, and tool use, making them promising candidates for autonomous agent applications. However, training LLM agents for complex…

机器学习 · 计算机科学 2025-12-09 Hanjiang Hu , Changliu Liu , Na Li , Yebin Wang

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon…

计算与语言 · 计算机科学 2025-08-04 Rana Salama , Jason Cai , Michelle Yuan , Anna Currey , Monica Sunkara , Yi Zhang , Yassine Benajiba

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

计算与语言 · 计算机科学 2025-07-18 Zijian Zhou , Ao Qu , Zhaoxuan Wu , Sunghwan Kim , Alok Prakash , Daniela Rus , Jinhua Zhao , Bryan Kian Hsiang Low , Paul Pu Liang

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

计算与语言 · 计算机科学 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies in the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation…

机器学习 · 计算机科学 2025-10-15 Nianyi Lin , Jiajie Zhang , Lei Hou , Juanzi Li

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…

Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, such as Group Relative Policy Optimization (GRPO), suffer from…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants…

人工智能 · 计算机科学 2026-04-21 Zhaokang Liao , Yingguo Gao , Yi Yang , Yongheng Hu , Jingting Ding

Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. Traditional approaches often depend on meticulously designed prompts, high-quality examples, or additional reward models for…

机器学习 · 计算机科学 2024-06-07 Muning Wen , Junwei Liao , Cheng Deng , Jun Wang , Weinan Zhang , Ying Wen

Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct)…

人工智能 · 计算机科学 2025-09-09 Chunlong Wu , Ye Luo , Zhibo Qu , Min Wang

Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory…

计算与语言 · 计算机科学 2026-05-29 Redacted by arXiv

Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interactions. Existing memory systems mainly rely on static,…

计算与语言 · 计算机科学 2026-05-04 Derong Xu , Shuochen Liu , Pengfei Luo , Pengyue Jia , Yingyi Zhang , Yi Wen , Yimin Deng , Wenlin Zhang , Enhong Chen , Xiangyu Zhao , Tong Xu

Large Language Models (LLMs) perform well in language tasks but often lack collaborative awareness and struggle to optimize global performance in multi-agent settings. We present a reinforcement learning-augmented LLM agent framework that…

人工智能 · 计算机科学 2026-01-01 Dong Qiu , Duo Xu , Limengxi Yue
‹ 上一页 1 2 3 10 下一页 ›