SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

• URL: http://arxiv.org/abs/2502.04780v1
• Date: Fri, 07 Feb 2025 09:33:44 GMT
• Title: SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
• Authors: Wanjia Zhao, Mert Yuksekgonul, Shirley Wu, James Zou,
• Abstract summary: Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks.<n>We introduce SiriuS, a self-improving, reasoning-driven optimization framework for multi-agent systems.<n>We show that SiriuS enhances multi-agent performance while generating reusable data for self-correction and self-play enhancement.
• Score: 21.94477076055433
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prompts and heuristics, making optimization difficult. A key challenge in optimizing multi-agent systems is acquiring suitable training data for specialized agents. We introduce SiriuS, a self-improving, reasoning-driven optimization framework for multi-agent systems. Central to our approach is the construction of an experience library: a repository of high-quality reasoning trajectories. The library is built by retaining reasoning steps that lead to successful outcomes, providing a robust training set for optimizing multi-agent system. Additionally, we introduce a library augmentation procedure that refines unsuccessful trajectories, further enriching the library. SiriuS boosts performance by 2.86\% to 21.88\% on reasoning and biomedical QA and enhances agent negotiation in competitive settings. Our results show that SiriuS enhances multi-agent performance while generating reusable data for self-correction and self-play enhancement in the future.

Related papers

• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development. We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• Knowledge-Aware Iterative Retrieval for Multi-Agent Systems [0.0]
  We introduce a novel large language model (LLM)-driven agent framework. It iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. The proposed system supports both competitive and collaborative sharing of updated context.
  arXiv  Detail & Related papers  (2025-03-17T15:27:02Z)
• A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops [3.729242965449096]
  This paper introduces a framework for autonomously optimizing Agentic AI solutions across industries.<n>The framework achieves optimal performance without human input by autonomously generating and testing hypotheses.<n>Case studies show significant improvements in output quality, relevance, and actionability.
  arXiv  Detail & Related papers  (2024-12-22T20:08:04Z)
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning [71.2981957820888]
  We propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets. The framework initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. The generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality.
  arXiv  Detail & Related papers  (2024-11-21T02:30:53Z)
• 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.<n>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)
• SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [18.84439000902905]
  Current large language model (LLM)-based software agents often follow linear, sequential processes. We propose SWE-Search, a multi-agent framework that integrates Monte Carlo Tree Search (MCTS) with a self-improvement mechanism. This highlights the potential of self-evaluation driven search techniques in complex software engineering environments.
  arXiv  Detail & Related papers  (2024-10-26T22:45:56Z)
• Agent-Oriented Planning in Multi-Agent Systems [54.429028104022066]
  We propose AOP, a novel framework for agent-oriented planning in multi-agent systems. In this study, we identify three critical design principles of agent-oriented planning, including solvability, completeness, and non-redundancy. Extensive experiments demonstrate the advancement of AOP in solving real-world problems compared to both single-agent systems and existing planning strategies for multi-agent systems.
  arXiv  Detail & Related papers  (2024-10-03T04:07:51Z)
• Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents [44.34340798542]
  Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities. We propose a framework that combines guided Monte Carlo Tree Search (MCTS) search with a self-critique mechanism and iterative fine-tuning on agent interactions.
  arXiv  Detail & Related papers  (2024-08-13T20:52:13Z)
• EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms [55.77492625524141]
  EvoAgent is a generic method to automatically extend specialized agents to multi-agent systems. We show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents.
  arXiv  Detail & Related papers  (2024-06-20T11:49:23Z)
• Adaptive In-conversation Team Building for Language Model Agents [33.03550687362213]
  Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks. Our new adaptive team-building paradigm offers a flexible solution, realized through a novel agent design named Captain Agent. A comprehensive evaluation across six real-world scenarios demonstrates that Captain Agent significantly outperforms existing multi-agent methods.
  arXiv  Detail & Related papers  (2024-05-29T18:08:37Z)
• AIOS: LLM Agent Operating System [39.59087894012381]
  This paper proposes the architecture of AIOS (LLM-based AI Agent Operating System) under the context of managing LLM-based agents. It introduces a novel architecture for serving LLM-based agents by isolating resources and LLM-specific services from agent applications into an AIOS kernel. Using AIOS can achieve up to 2.1x faster execution for serving agents built by various agent frameworks.
  arXiv  Detail & Related papers  (2024-03-25T17:32:23Z)
• DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning [56.887047551101574]
  We present DS-Agent, a novel framework that harnesses large language models (LLMs) agent and case-based reasoning (CBR) In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which can flexibly capitalize on the expert knowledge from Kaggle. In the deployment stage, DS-Agent implements a low-resource deployment stage with a simplified CBR paradigm, significantly reducing the demand on foundational capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-02-27T12:26:07Z)

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.