English
Related papers

Related papers: Experiential Reflective Learning for Self-Improvin…

200 papers

Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement learning (RL) has emerged as a powerful paradigm for training these agents to perform…

Computation and Language · Computer Science 2026-05-11 Shiyu Li , Yang Tang , Yifan Wang , Peiming Li , Xi Chen

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Machine Learning · Computer Science 2025-10-21 Mengqi Liao , Xiangyu Xi , Ruinian Chen , Jia Leng , Yangen Hu , Ke Zeng , Shuai Liu , Huaiyu Wan

Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the…

Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large language models (LLMs), when integrated into well-designed frameworks (i.e.,…

Artificial Intelligence · Computer Science 2026-05-12 Haoze Lv , Ning Lu , Ziang Zhou , Shengcai Liu

There has been a growing interest in developing learner models to enhance learning and teaching experiences in educational environments. However, existing works have primarily focused on structured environments relying on meticulously…

Machine Learning · Computer Science 2024-05-01 Bahar Radmehr , Adish Singla , Tanja Käser

Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impractical. In this paper, we investigate the use of…

Computation and Language · Computer Science 2025-05-08 Zi-Yi Dou , Cheng-Fu Yang , Xueqing Wu , Kai-Wei Chang , Nanyun Peng

Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks…

Artificial Intelligence · Computer Science 2024-07-02 Rishav Bhagat , Jonathan Balloch , Zhiyu Lin , Julia Kim , Mark Riedl

Multi-agents has exhibited significant intelligence in real-word simulations with Large language models (LLMs) due to the capabilities of social cognition and knowledge retrieval. However, existing research on agents equipped with effective…

Artificial Intelligence · Computer Science 2025-04-23 Yajie Yu , Yue Feng

Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each…

Machine Learning · Computer Science 2021-10-29 Archit Sharma , Abhishek Gupta , Sergey Levine , Karol Hausman , Chelsea Finn

We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model…

Computation and Language · Computer Science 2026-03-20 Xiaoyin Chen , Canwen Xu , Yite Wang , Boyi Liu , Zhewei Yao , Yuxiong He

Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. However, exploration remains a central challenge in RL for LLM…

Machine Learning · Computer Science 2026-03-03 Andrew Szot , Michael Kirchhof , Omar Attia , Alexander Toshev

The lack of domain-specific data in the pre-training of Large Language Models (LLMs) severely limits LLM-based decision systems in specialized applications, while post-training a model in the scenarios requires significant computational…

Artificial Intelligence · Computer Science 2025-05-05 Zongyuan Li , Pengfei Li , Runnan Qi , Yanan Ni , Lumin Jiang , Hui Wu , Xuebo Zhang , Kuihua Huang , Xian Guo

Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation, yet existing research has mostly evaluated their adherence to…

Artificial Intelligence · Computer Science 2025-10-14 Enric Junque de Fortuny , Veronica Roberta Cappelli

Episodic training, where an agent's environment is reset after every success or failure, is the de facto standard when training embodied reinforcement learning (RL) agents. The underlying assumption that the environment can be easily reset…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Zichen Zhang , Luca Weihs

Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. However, current LLMs that learn from human or external model supervision are costly and may face performance ceilings as task…

Computation and Language · Computer Science 2024-06-04 Zhengwei Tao , Ting-En Lin , Xiancai Chen , Hangyu Li , Yuchuan Wu , Yongbin Li , Zhi Jin , Fei Huang , Dacheng Tao , Jingren Zhou

Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term…

Computation and Language · Computer Science 2023-10-31 Danyang Zhang , Lu Chen , Situo Zhang , Hongshen Xu , Zihan Zhao , Kai Yu

Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents…

Artificial Intelligence · Computer Science 2025-12-16 Emre Can Acikgoz , Jinoh Oh , Jie Hao , Joo Hyuk Jeon , Heng Ji , Dilek Hakkani-Tür , Gokhan Tur , Xiang Li , Chengyuan Ma , Xing Fan

A common challenge in reinforcement learning is how to convert the agent's interactions with an environment into fast and robust learning. For instance, earlier work makes use of domain knowledge to improve existing reinforcement learning…

Machine Learning · Computer Science 2020-04-01 Yannis Flet-Berliac , Philippe Preux

Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the…

Machine Learning · Computer Science 2026-04-22 Zhiyin Yu , Bo Zhang , Qibin Hou , Zhonghai Wu , Xiao Luo , Lei Bai

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs). Despite its efficacy, RLVR faces a meta-learning bottleneck: it lacks…

Machine Learning · Computer Science 2026-02-12 Shiting Huang , Zecheng Li , Yu Zeng , Qingnan Ren , Zhen Fang , Qisheng Su , Kou Shi , Lin Chen , Zehui Chen , Feng Zhao