← 研踪 PaperTrailarXiv:2602.14697 · v4
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
首次提交 2026-02-16 20:34
版本更新 2026-11-04 16:38
雷达观测 2026-11-05 12:13
摘要
Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement learning (RL) for weight updates. In this work, we propose Evolutionary System Prompt Learning (E-SPL), a method for jointly improving a model's experiential context and its weights. In each RL iteration, E-SPL samples trajectories under multiple system prompts in parallel, then uses them to jointly update the weights with RL and evolve the system prompts with self-reflection. E-SPL encourages a natural division between procedural knowledge in weights and interpretable declarative knowledge in system prompts. Most notably, in an easy-to-hard generalization setting (AIME $\rightarrow$ BeyondAIME), E-SPL improves RL success rate from 38.8% $\rightarrow$ 45.1%. E-SPL also improves RL on AIME 2025 (56.3% $\rightarrow$ 60.6%), HMMT 2025 (50.0% $\rightarrow$ 52.7%), and agentic search (44.2% $\rightarrow$ 48.6% on gpt-oss-120b). Across all settings, E-SPL outperforms both RL-only and evolution-only baselines, demonstrating that weight updates and context updates are deeply synergistic and can together yield gains in generalization that neither achieves alone. Code is available at https://github.com/LunjunZhang/E-SPL.
作者备注：NeurIPS 2026
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v4 · 2026-11-04 16:38 · 最新观测版本
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement learning (RL) for weight updates. In this work, we propose Evolutionary System Prompt Learning (E-SPL), a method for jointly improving a model's experiential context and its weights. In each RL iteration, E-SPL samples trajectories under multiple system prompts in parallel, then uses them to jointly update the weights with RL and evolve the system prompts with self-reflection. E-SPL encourages a natural division between procedural knowledge in weights and interpretable declarative knowledge in system prompts. Most notably, in an easy-to-hard generalization setting (AIME $\rightarrow$ BeyondAIME), E-SPL improves RL success rate from 38.8% $\rightarrow$ 45.1%. E-SPL also improves RL on AIME 2025 (56.3% $\rightarrow$ 60.6%), HMMT 2025 (50.0% $\rightarrow$ 52.7%), and agentic search (44.2% $\rightarrow$ 48.6% on gpt-oss-120b). Across all settings, E-SPL outperforms both RL-only and evolution-only baselines, demonstrating that weight updates and context updates are deeply synergistic and can together yield gains in generalization that neither achieves alone. Code is available at https://github.com/LunjunZhang/E-SPL.
查看此版本解读 →查看此版本原文 ↗