3 papers
cs.AI2026
Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents
Zechuan Wang, Siyuan Lu, Hongxuan Zhang +3
Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its trajectory-level credit assignm…
cs.AI2026
RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents
Ruishan Fang, Siyuan Lu, Chenyi Zhuang +1
Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the…
cs.AI2025
Don't Just Fine-tune the Agent, Tune the Environment
Siyuan Lu, Zechuan Wang, Hongxuan Zhang +5
Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality trainin…