paper-with-me

Papers

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes

2025-06-17 · 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

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.

📄 PDF Abstract BibTeX arXiv:2506.14728

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Healthcare AI GYM for Medical Agents

2026-05-01 · Minbyul Jeong arxiv

Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisions -- yet a unified training environment provides the breadth of cli…

Reinforcement Learning

Weak-to-Strong Knowledge Distillation Accelerates Visual Learning

2026-04-16 · Baiang Li, Wenhao Chai, Felix Heide arxiv

Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression or final-accuracy improvement. We instead…

Knowledge DistillationObject Detection

EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning

2025-10-20 · He Du, Bowen Li, Aijun Yang, Siyang He 외 arxiv

Reliable verifiable data has become a key driver of capability gains in modern language models, enabling stable reinforcement learning with verifiable rewards and effective distillation that transfers competence across m…

Reinforcement Learning

Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors

2025-05-16 · Lang Feng, Jiahao Lin, Dong Xing, Li Zhang 외

Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing self-play-based methods are constrained …

Knowledge DistillationMulti-agent Reinforcement Learning

Training Generalizable Collaborative Agents via Strategic Risk Aversion

2026-02-25 · Chengrui Qu, Yizhou Zhang, Nicolas Lanzetti, Eric Mazumdar arxiv

Many emerging agentic paradigms require agents to collaborate with one another (or people) to achieve shared goals. Unfortunately, existing approaches to learning policies for such collaborative problems produce brittle …

Multi-agent Reinforcement Learning