NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents

arXiv:2609.33379 · cs.CL, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

• Benchmark — 65× in this paper · explained in 2 episodes
• Accuracy — 34× in this paper · explained in 1 episode
• Trace — 27× in this paper · explained in 2 episodes
• Verification — 16× in this paper · explained in 2 episodes
• Ablation — 12× in this paper · explained in 1 episode
• Natural-Language Policy Gradients — 9× in this paper
• Calibration — 4× in this paper · explained in 7 episodes
• Credit assignment — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• GRPO — 3× in this paper · explained in 6 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Topological Order — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Computational overhead — 2× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 2× in this paper · explained in 3 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• HaluMem: Evaluating Hallucinations in Memory Systems of Agents
• MemR$^3$: Memory Retrieval via Reflective Reasoning for LLM Agents
• MemGPT: Towards LLMs as Operating Systems
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Qwen3 Technical Report
• Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
• Large Language Models Are Human-Level Prompt Engineers

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering