AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes

• URL: http://arxiv.org/abs/2506.14728v1
• Date: Tue, 17 Jun 2025 17:08:32 GMT
• Title: AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
• Authors: Jiahao Qiu, Xinzhe Juan, Yimin Wang, Ling Yang, Xuan Qi, Tongcheng Zhang, Jiacheng Guo, Yifu Lu, Zixin Yao, Hongru Wang, Shilong Liu, Xun Jiang, Liu Leqi, Mengdi Wang,
• Abstract summary: We propose a novel, training-free agent distillation framework that enables scalable knowledge transfer via direct reuse of Model-Context-Protocols (MCPs)<n>MCPs are structured and reusable task-solving modules autonomously generated by teacher agents.<n>Experiments on biomedical and mathematical benchmarks demonstrate that our distilled student agents, built on small language models, can achieve performance comparable to advanced systems.
• Score: 35.504027343665605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning, memory, and tool use, remains relatively underexplored. Existing agent distillation methods typically replay full teacher trajectories or imitate step-by-step teacher tool usage, but they often struggle to train student agents to dynamically plan and act in novel environments. We propose AgentDistill, a novel, training-free agent distillation framework that enables efficient and scalable knowledge transfer via direct reuse of Model-Context-Protocols (MCPs), which are structured and reusable task-solving modules autonomously generated by teacher agents. The reuse of these distilled MCPs enables student agents to generalize their capabilities across domains and solve new problems with minimal supervision or human intervention. Experiments on biomedical and mathematical benchmarks demonstrate that our distilled student agents, built on small language models, can achieve performance comparable to advanced systems using large LLMs such as OctoTools (GPT-4o), highlighting the effectiveness of our framework in building scalable and cost-efficient intelligent agents.

Related papers

• AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents [25.735754822676277]
  Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks.<n> reinforcement learning (RL) has been explored to enhance LM's capabilities, such as reasoning and factuality.<n>We built AgentFly, a scalable and Agent-RL framework designed to empower LM agents with a variety of RL algorithms.
  arXiv  Detail & Related papers  (2025-07-20T10:22:36Z)
• Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking [61.61356842567952]
  We propose STeP, a novel method for improving LLM-based agent training.<n>We synthesize self-reflected trajectories that include reflections and corrections of error steps.<n>Experiments demonstrate that our method improves agent performance across three representative tasks.
  arXiv  Detail & Related papers  (2025-05-26T14:11:12Z)
• Distilling LLM Agent into Small Models with Retrieval and Code Tools [57.61747522001781]
  Agent Distillation is a framework for transferring reasoning capability and task-solving behavior from large language models into small language models.<n>Our results show that sLMs as small as 0.5B, 1.5B, 3B parameters can achieve performance competitive with next-tier larger 1.5B, 3B, 7B models.
  arXiv  Detail & Related papers  (2025-05-23T08:20:15Z)
• Structured Agent Distillation for Large Language Model [58.22497891295258]
  We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models.<n>Our method segments trajectories into [REASON] and [ACT] spans, applying segment-specific losses to align each component with the teacher's behavior.<n>Experiments on ALFWorld, HotPotQA-ReAct, and WebShop show that our approach consistently outperforms token-level and imitation learning baselines.
  arXiv  Detail & Related papers  (2025-05-20T02:01:55Z)
• LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners [51.518410910148816]
  Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time.<n>We present LifelongAgentBench, the first unified benchmark designed to systematically assess the lifelong learning ability of LLM agents.
  arXiv  Detail & Related papers  (2025-05-17T10:09:11Z)
• Improving Retrospective Language Agents via Joint Policy Gradient Optimization [57.35348425288859]
  RetroAct is a framework that jointly optimize both task-planning and self-reflective evolution capabilities in language agents.<n>We develop a two-stage joint optimization process that integrates imitation learning and reinforcement learning.<n>We conduct extensive experiments across various testing environments, demonstrating RetroAct has substantial improvements in task performance and decision-making processes.
  arXiv  Detail & Related papers  (2025-03-03T12:54:54Z)
• Offline Training of Language Model Agents with Functions as Learnable Weights [39.88545362699836]
  We present a novel paradigm of training Large Language Models (LLMs) agents without modifying the LLM weights. We develop Agentr that employs the LLM to update agents' functions and devise an agent training algorithm with two strategies, roll-back, and early-stop. With extensive experiments, we showcase that the agent training paradigm could significantly improve the performance of representative LLM agents.
  arXiv  Detail & Related papers  (2024-02-17T18:31:21Z)
• Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents [16.24662355253529]
  Large Language Models (LLMs) can address sequential decision-making tasks through the provision of high-level instructions. LLMs lack specialization in tackling specific target problems, particularly in real-time dynamic environments. We introduce a novel framework that addresses these challenges by training a smaller, specialized student RL agent using instructions from an LLM-based teacher agent.
  arXiv  Detail & Related papers  (2023-11-22T13:15:42Z)
• MADiff: Offline Multi-agent Learning with Diffusion Models [79.18130544233794]
  MADiff is a diffusion-based multi-agent learning framework.<n>It works as both a decentralized policy and a centralized controller.<n>Our experiments demonstrate that MADiff outperforms baseline algorithms across various multi-agent learning tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:14:09Z)

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.