← Search

Fangchen Dong

2 accepted papers

2026

Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning

ICML 2026poster

Reinforcement learning significantly enhances LLM capabilities but suffers from a critical issue: length inflation, where models adopt verbosity or inefficient reasoning to maximize rewards. Prior approaches struggle to address this challenge in a general and lossless manner, primarily because addit…

Cited by 0SourceScholar
2026

TaskCraft: Automated Generation of Agentic Tasks

ICLR 2026poster

Agentic tasks, which require multistep problem solving with tool use and adaptive reasoning, are becoming increasingly central to the advancement of NLP and AI. Although benchmarks such as GAIA and BrowseComp have advanced agent evaluation, their scalability remains limited by the high cost of human…

Cited by 0SourcecodeScholar