papers

Publications (18)

cs.CL2026

Are Full Rollouts Necessary for On-Policy Distillation?

Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7

On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm…

cs.CV2026

Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning

Jingbo Sun, Qichao Zhang, Songjun Tu +5

Zero-shot unsupervised reinforcement learning (URL) offers a promising direction for building generalist agents capable of generalizing to unseen tasks without additional supervisi…

cs.LG2026

One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs

Di He, Songjun Tu, Keyu Wang +2

Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural…

cs.AI2026

AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning

Jingbo Sun, Wenyue Chong, Songjun Tu +7

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. Howeve…

cs.AI2026

MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents

Yiwen Ma, Songjun Tu, Qichao Zhang +3

Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evidence paradigm assumes retri…

cs.CL2025

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

Songjun Tu, Jiahao Lin, Xiangyu Tian +8

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. Ho…