Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2410.06101v2
• Date: Sat, 22 Feb 2025 17:08:44 GMT
• Title: Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
• Authors: Hao Ma, Tianyi Hu, Zhiqiang Pu, Boyin Liu, Xiaolin Ai, Yanyan Liang, Min Chen,
• Abstract summary: Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks.<n>In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework.<n>Results show that CORY outperforms PPO in terms of policy optimality, resistance to distribution collapse, and training robustness.
• Score: 13.753960633998389
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though these algorithms are effective in general RL settings, they often exhibit suboptimal performance and vulnerability to distribution collapse when applied to the fine-tuning of LLMs. In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework, to leverage the inherent coevolution and emergent capabilities of multi-agent systems. In CORY, the LLM to be fine-tuned is initially duplicated into two autonomous agents: a pioneer and an observer. The pioneer generates responses based on queries, while the observer generates responses using both the queries and the pioneer's responses. The two agents are trained together. During training, the agents exchange roles periodically, fostering cooperation and coevolution between them. Experiments evaluate CORY's performance by fine-tuning GPT-2 and Llama-2 under subjective and objective reward functions on the IMDB Review and GSM8K datasets, respectively. Results show that CORY outperforms PPO in terms of policy optimality, resistance to distribution collapse, and training robustness, thereby underscoring its potential as a superior methodology for refining LLMs in real-world applications.

Related papers

• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Omni-Thinker: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards [50.21528417884747]
  We introduce Omni-Thinker, a unified reinforcement learning framework that enhances large language models (LLMs) performance across diverse tasks.<n>Our approach enables consistent optimization across task types and scales RL-based training to subjective domains.<n> Experimental results across four domains reveal that curriculum learning improves performance by 5.2% over joint training and 9.1% over model merging.
  arXiv  Detail & Related papers  (2025-07-20T01:50:16Z)
• RLAE: Reinforcement Learning-Assisted Ensemble for LLMs [21.77261258691006]
  Large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks.<n>We propose Reinforcement Learning-Assisted Ensemble for LLMs, a novel framework that reformulates ensemble through the lens of a Markov Decision Process (MDP)<n>Our approach introduces a RL agent that dynamically adjusts ensemble weights by considering both input context and intermediate generation states.
  arXiv  Detail & Related papers  (2025-05-31T07:38:41Z)
• Co-Reinforcement Learning for Unified Multimodal Understanding and Generation [53.03303124157899]
  This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs)<n>We introduce CoRL, a co-reinforcement learning framework comprising a unified RL stage for joint optimization and a refined RL stage for task-specific enhancement.<n>With the proposed CoRL, our resulting model, ULM-R1, achieves average improvements of 7% on three text-to-image generation datasets and 23% on nine multimodal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-05-23T06:41:07Z)
• An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents [34.25887147052966]
  Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving.<n>More recently, RL has been leveraged to create sophisticated LLM-based search agents that adeptly combine reasoning with search engine use.<n>Key factors -- such as (1) reward formulation, (2) the choice and characteristics of the underlying LLM, and (3) the role of the search engine in the RL process -- require further investigation.
  arXiv  Detail & Related papers  (2025-05-21T05:09:43Z)
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning [125.65034908728828]
  Training large language models (LLMs) as interactive agents presents unique challenges. While reinforcement learning has enabled progress in static tasks, multi-turn agent RL training remains underexplored. We propose StarPO, a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents.
  arXiv  Detail & Related papers  (2025-04-24T17:57:08Z)
• SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks [110.20297293596005]
  Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. Existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while leveraging the generalization capabilities of LLMs. We propose a novel RL algorithm, SWEET-RL, that uses a carefully designed optimization objective to train a critic model with access to additional training-time information. Our experiments demonstrate that SWEET-RL achieves a 6% absolute improvement in success and win rates on ColBench compared to other state-of-the-art multi-turn RL algorithms.
  arXiv  Detail & Related papers  (2025-03-19T17:55:08Z)
• MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning [26.736078756799635]
  We introduce a new post-training paradigm MAPoRL (Multi-Agent Post-co-training for collaborative LLMs with Reinforcement Learning) In MAPoRL, multiple LLMs first generate their own responses independently and engage in a multi-turn discussion to collaboratively improve the final answer. A MAPoRL verifier evaluates both the answer and the discussion, by assigning a score that verifies the correctness of the answer. The score serves as the co-training reward, and is then maximized through multi-agent RL.
  arXiv  Detail & Related papers  (2025-02-25T18:33:48Z)
• C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation [13.120930059424975]
  C-3PO is a proxy-centric framework that facilitates communication between retrievers and large language models. Our framework implements three specialized agents that collaboratively optimize the entire RAG pipeline.
  arXiv  Detail & Related papers  (2025-02-10T07:04:32Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities. We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [66.9481561915524]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps. On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• Teaching Large Language Models to Reason with Reinforcement Learning [38.17625148525193]
  Reinforcement Learning from Human Feedback (textbfRLHF) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from feedback.
  arXiv  Detail & Related papers  (2024-03-07T16:36:29Z)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [80.10358123795946]
  We develop a framework for building multi-turn RL algorithms for fine-tuning large language models. Our framework adopts a hierarchical RL approach and runs two RL algorithms in parallel. Empirically, we find that ArCHer significantly improves efficiency and performance on agent tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:45:56Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning [37.10401435242991]
  Large language models (LLMs) often fail in solving simple decision-making tasks due to misalignment of the knowledge in LLMs with environments. We propose TWOSOME, a novel framework that deploys LLMs as decision-making agents to efficiently interact and align with embodied environments via RL.
  arXiv  Detail & Related papers  (2024-01-25T13:03:20Z)
• PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation [65.268245109828]
  We introduce PRILoRA, which linearly allocates a different rank for each layer, in an increasing manner, and performs pruning throughout the training process. We validate the effectiveness of PRILoRA through extensive experiments on eight GLUE benchmarks, setting a new state of the art.
  arXiv  Detail & Related papers  (2024-01-20T20:25:17Z)
• Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization [0.0]
  We introduce a method to address goal misgeneralization in reinforcement learning (RL) Goal misgeneralization occurs when an agent retains its capabilities out-of-distribution yet pursues a proxy rather than the intended one. This study demonstrates how the Large Language Model can efficiently supervise RL agents.
  arXiv  Detail & Related papers  (2024-01-14T01:09:48Z)
• Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Case Study [1.3597551064547502]
  We employ a teacher-student learning framework to tackle problems of Large Language Models (LLMs) and reinforcement learning (RL) models. Within this framework, the LLM acts as a teacher, while the RL model acts as a student. We propose a practical algorithm to address the problem and conduct empirical experiments to evaluate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-01-12T14:35:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.