5 citations · 17 across the 27 of their papers we have counts for
3 papers · 1 filter
Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use
Zixiang Chen, Wenting Zhao, Zhepeng Cen +9
Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When rewards depend on later inter…
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Cheng Qian, Wenting Zhao, Liangwei Yang +6
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, a…
Multi-Turn Code Generation Through Single-Step Rewards
Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Wayne Chen +3
We address the problem of code generation from multi-turn execution feedback. Existing methods either generate code without feedback or use complex, hierarchical reinforcement lear…