Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Contextual Credit Policy Optimization
Huiwen Han, Ziyao Zeng, Zihao Zhu +6
Group-based reinforcement learning enables large language model agents to learn from sparse outcome rewards in long-horizon tasks. Recent methods derive step-level credit by compar…
cs.LG2026
Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
Huaiyu Fu, Heng Cao, Hao Wang +2
LLM agents often admit multiple high-quality solutions to the same task, differing in reasoning structure, tool-use pattern, or interaction trajectory. Yet existing notions of dive…