26 papers
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
Tianzhu Ye, Li Dong, Guanheng Chen +4
Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with dis…
Online Experiential Learning for Language Models
Tianzhu Ye, Li Dong, Qingxiu Dong +3
The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated dur…
BitNet Text Embeddings
Zhen Li, Xin Huang, Liang Wang +8
LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding i…
Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
Yunan Wang, Minghui Song, Zihan Zhang +6
Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL fra…
Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
Qibin Wang, Pu Zhao, Shaohan Huang +6
Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting are limited as their performance depe…
On-Policy Context Distillation for Language Models
Tianzhu Ye, Li Dong, Xun Wu +2
Context distillation enables language models to internalize in-context knowledge into their parameters. In our work, we propose On-Policy Context Distillation (OPCD), a framework t…