NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents
Large language model agents increasingly rely on compound programs for retrieval, tool use, reasoning, and verification, yet their failures often arise from local procedural decisions. Existing reinforcement-learning and prompt-optimization approaches typically rely on scalar rewards or repeatedly modify entire prompts...
Xu Liu, Wen-Zhang Wei, Jun Cao et al.
· 0 citations