MALT: Improving Reasoning with Multi-Agent LLM Training

• URL: http://arxiv.org/abs/2412.01928v1
• Date: Mon, 02 Dec 2024 19:30:36 GMT
• Title: MALT: Improving Reasoning with Multi-Agent LLM Training
• Authors: Sumeet Ramesh Motwani, Chandler Smith, Rocktim Jyoti Das, Markian Rybchuk, Philip H. S. Torr, Ivan Laptev, Fabio Pizzati, Ronald Clark, Christian Schroeder de Witt,
• Abstract summary: We present a first step toward "Multi-agent LLM training" (MALT) on reasoning problems. Our approach employs a sequential multi-agent setup with heterogeneous LLMs assigned specialized roles. We evaluate our approach across MATH, GSM8k, and CQA, where MALT on Llama 3.1 8B models achieves relative improvements of 14.14%, 7.12%, and 9.40% respectively.
• Score: 64.13803241218886
• License:
• Abstract: Enabling effective collaboration among LLMs is a crucial step toward developing autonomous systems capable of solving complex problems. While LLMs are typically used as single-model generators, where humans critique and refine their outputs, the potential for jointly-trained collaborative models remains largely unexplored. Despite promising results in multi-agent communication and debate settings, little progress has been made in training models to work together on tasks. In this paper, we present a first step toward "Multi-agent LLM training" (MALT) on reasoning problems. Our approach employs a sequential multi-agent setup with heterogeneous LLMs assigned specialized roles: a generator, verifier, and refinement model iteratively solving problems. We propose a trajectory-expansion-based synthetic data generation process and a credit assignment strategy driven by joint outcome based rewards. This enables our post-training setup to utilize both positive and negative trajectories to autonomously improve each model's specialized capabilities as part of a joint sequential system. We evaluate our approach across MATH, GSM8k, and CQA, where MALT on Llama 3.1 8B models achieves relative improvements of 14.14%, 7.12%, and 9.40% respectively over the same baseline model. This demonstrates an early advance in multi-agent cooperative capabilities for performance on mathematical and common sense reasoning questions. More generally, our work provides a concrete direction for research around multi-agent LLM training approaches.

Related papers

• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks. However, they still struggle with problems requiring multi-step decision-making and environmental feedback. We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Mars-PO: Multi-Agent Reasoning System Preference Optimization [16.145823558485393]
  We propose Mars-PO, a novel framework to improve the mathematical reasoning capabilities of large language models (LLMs) It combines high-quality outputs from multiple agents into a hybrid positive sample set and pairs them with agent-specific negative samples to construct robust preference pairs for training. By aligning agents with shared positive samples while addressing individual weaknesses, Mars-PO achieves substantial performance improvements on mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-11-28T10:35:16Z)
• 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)
• Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning [13.753960633998389]
  Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework. Results show that CORY outperforms PPO in terms of policy optimality, resistance to distribution collapse, and training robustness.
  arXiv  Detail & Related papers  (2024-10-08T14:55:26Z)
• Optimizing Collaboration of LLM based Agents for Finite Element Analysis [1.5039745292757671]
  This paper investigates the interactions between multiple agents within Large Language Models (LLMs) in the context of programming and coding tasks. We utilize the AutoGen framework to facilitate communication among agents, evaluating different configurations based on the success rates from 40 random runs for each setup.
  arXiv  Detail & Related papers  (2024-08-23T23:11:08Z)
• 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)
• LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions [8.55917897789612]
  We focus on the cooperative tasks of multiple agents with a common goal and communication among them. We also consider human-in/on-the-loop scenarios enabled by the language component in the framework.
  arXiv  Detail & Related papers  (2024-05-17T22:10:23Z)
• Large Language Model-based Human-Agent Collaboration for Complex Task Solving [94.3914058341565]
  We introduce the problem of Large Language Models (LLMs)-based human-agent collaboration for complex task-solving. We propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process.
  arXiv  Detail & Related papers  (2024-02-20T11:03:36Z)
• AdaMerging: Adaptive Model Merging for Multi-Task Learning [68.75885518081357]
  This paper introduces an innovative technique called Adaptive Model Merging (AdaMerging) It aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data. Compared to the current state-of-the-art task arithmetic merging scheme, AdaMerging showcases a remarkable 11% improvement in performance.
  arXiv  Detail & Related papers  (2023-10-04T04:26:33Z)

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.