paper-with-me

Papers

Building Multi-Task Agentic LLMs via Two-Phase Distillation

2026-06-29 · Huaijie Wang, Shusheng Xu, Yi Wu, Kaifeng Lyu arxiv

A key step toward artificial general intelligence is to train models that can perform multiple tasks. In this paper, we study how to build such models by first training separate RL experts for individual tasks and then consolidating them via distillation, as an alternative to directly training a single model on mixed tasks. We show that off-policy distillation degrades in multi-task settings due to the mode-covering nature of forward KL: aggregating data from multiple tasks introduces a large number of behavioral modes that can exceed the student's capacity, forcing it to average across behaviors and leading to degraded performance. In contrast, on-policy distillation is mode-seeking but requires strong initialization. Inspired by these observations, we propose a two-phase approach: off-policy distillation followed by on-policy refinement. Evaluation across conversational agents and text-based games confirms that this two-phase approach matches single-task RL expert performance for each individual task, whereas off-policy or on-policy distillation alone fails to match this performance.

📄 PDF Abstract BibTeX arXiv:2606.30044

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI

2025-10-19 · Jitao Sang, Jinlin Xiao, Jiarun Han, Jilin Chen 외 arxiv

The rapid evolution of agentic AI marks a new phase in artificial intelligence, where Large Language Models (LLMs) no longer merely respond but act, reason, and adapt. This survey traces the paradigm shift in building ag…

Reinforcement Learning

ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction

2025-08-18 · Xingshan Zeng, Weiwen Liu, Lingzhi Wang, Liangyou Li 외 arxiv

Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions, often involving complex function calls and dynamic user-agent exchanges. Existing simulation-based data generation meth…

Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation

2025-06-10 · Xiaowen Ma, Chenyang Lin, Yao Zhang, Volker Tresp 외

Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcom…

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

2026-05-19 · Haiquan Lu, Zigeng Chen, Gongfan Fang, Xinyin Ma 외 arxiv

LLM agents have recently emerged as a powerful paradigm for solving complex tasks through planning, tool use, memory retrieval, and multi-step interaction. However, these agentic workflows often introduce substantial inp…

AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

2025-10-05 · Hanchen Zhang, Xiao Liu, Bowen Lv, Xueqiao Sun 외 arxiv

Recent advances in large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions. However, applying reinforcement learning (RL) to train LLM agents in…

Reinforcement Learning