4 papers
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
Boyan Li, Bingsen Chen, Chenghao Yang +3
Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have emerged as two dominant methods for post-training reasoning LLMs. Prior work uses OPD's…
Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision
Bingsen Chen, Boyan Li, Ping Nie +3
Existing benchmarks for Deep Research Agents (DRAs) treat report generation as a single-shot writing task, which fundamentally diverges from how human researchers iteratively draft…
RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
Zhilong Chen, Chengzong Zhao, Boyuan Chen +9
Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present…
Inter-Passage Verification for Multi-evidence Multi-answer QA
Bingsen Chen, Shengjie Wang, Xi Ye +1
Multi-answer question answering (QA), where questions can have many valid answers, presents a significant challenge for existing retrieval-augmented generation-based QA systems, as…