RL for LLM Agents

RL: Reinforcement Learning · LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

70 papers in the last four weeks, up 141% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 402

All topics

Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning
Feb 1, 2026Yu Li, Mingyang Yi, Xiuyu Li +6RL for Language Model Reasoning Gradient Interference
School of Information, Renmin University of China, Beijing, China · Bytedance Inc., Beijing, China · Bytedance Inc., San Jose, USA
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
Jan 26, 2026Yibo Li, Zijie Lin, Ailin Deng +5Continual Learning for LLM Agents Reinforcement Learning
National University of Singapore, Singapore.
CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning
Jan 21, 2026Tianshi Xu, Yuteng Chen, Meng LiAgentic RL Reinforcement Learning
Peking University · NTU, Singapore
PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning
Jan 17, 2026Bingxuan Li, Jeonghwan Kim, Cheng Qian +4Long-Horizon Agent Tasks RL for LLM Agents
University of Illinois at Urbana-Champaign · Viven
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
Jan 9, 2026Zhiyu Shen, Ziming Wu, Fuming Lai +2Reinforcement Learning Memory-Augmented Language Models
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · Tencent Inc.
AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
Dec 18, 2025Tzu-Han Lin, Wei-Lin Chen, Chen-An Li +3Retrieval-Augmented Generation Knowledge Augmentation for Language Models
National Taiwan University · Department of Computer Science, University of Virginia
Iterative GRPO: Batch-Online Policy Iteration for Multi-Turn RL via Single-Turn RLHF
Nov 26, 2025Daniel R. Jiang, Ankur Samanta, Yukai Yang +3Reinforcement Learning Policy Iteration
Meta · FAIR at Meta
Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization
Nov 25, 2025Chenliang Li, Adel Elmahdy, Alex Boyd +7RL for Language Model Reasoning Importance Sampling
Texas A&M University · GE HealthCare · Independent Researcher +1
Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
Oct 16, 2025Shiqi Chen, Tongyao Zhu, Zian Wang +8RL Exploration Policy Learning
City University of Hong Kong · National University of Singapore · The Hong Kong Polytechnic University +5
Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents
Feb 6, 2025Selim Furkan Tekin, Gaowen Liu, Ramana Rao Kompella +1Multi-Agent LLM Systems Language Model Ensembles
Georgia Institute of Technology · Cisco Systems
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
Date pendingZhizhao Guan, Chen Huang, Ziming Liu +5RL Exploration LLM Agents
Sichuan University · Engineering Research Center of Machine Learning and Industry Intelligence · National University of Singapore +1
CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution
Date pendingJinyuan Feng, Dongmin Li, Yiqun Chen +4Hierarchical RL LLM Agent Skill Learning
Institute of Automation, Chinese Academy of Sciences · Renmin University of China · ByteDance

Feb 1, 2026, cs.AIJ/K move · Enter open · S save

Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning

Yu Li, Mingyang Yi, Xiuyu Li, Ju Fan+5

School of Information, Renmin University of China, Beijing, China · Bytedance Inc., Beijing, China · Bytedance Inc., San Jose, USA

RL for Language Model Reasoning Gradient Interference Agentic Reasoning RL for LLM Agents RL for Tool Use

Open paper AskPDF arXiv

Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most existing ARL methods train a single set of parameters to support both reasoning and tool-use behaviors, implicitly assuming that joint training leads to improved overall agent performance. Despite its widespread adoption, this assumption has rarely been examined empirically. In this paper, we systematically examine this assumption by introducing Capability Effect Attribution (CEA), which provides quantitative evidence of interference between reasoning and tool-use behaviors. Through an in-depth analysis, we show that these two capabilities often induce misaligned gradient directions, leading to training interference that undermines the effectiveness of joint optimization and challenges the prevailing ARL paradigm. To address this issue, we propose Disentangled Action--Reasoning Tuning (DART), a simple and efficient framework that explicitly decouples parameter updates for reasoning and tool use via separate low-rank adaptation modules. With this simple change alone, DART outperforms all joint-optimization baselines and approaches the 2-Agent upper bound across thirteen benchmarks on retrieval-augmented QA and NL2SQL, further supporting our finding of capability interference under shared optimization.

Momentum

Related topics

Latest papers 402