作者位次 #5/7ACL 2026Poster· Natural Language Processing
WIST : Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
Fangyuan Li · Pengfei Li · Shijie Wang · Junqi Gao · Jianxing Liu · Biqing Qi · Yuqiang Li
摘要
Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improving language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while corpus-grounded approaches rely on curated data environments. We pre...