AI 智能体学会「贝叶斯」式自我进化
现在的 AI 智能体（比如帮你写代码、做分析的助手）经常需要外部「技能包」——提示词、工具、记忆、标准操作流程。以前这些技能靠人工试错或简单重复成功案例来更新，像盲人摸象。这篇论文让智能体用贝叶斯推理来管理技能：它把每个技能看作一个「假设」，然后根据实际执行结果（成功或失败）不断更新这个假设的可信度，就像科学家做实验一样。系统会自动决定是修补、拆分、压缩、淘汰还是探索新技能。在多个测试中，任务成功率从80%提升到95%，甚至从45%跃升到65%。这不是你明天就能用的工具，但它展示了一个方向：AI 智能体可以像人一样，从经验中学习并优化自己的行为策略，而不是靠堆砌提示词。
📄 原文摘要(英文)
LLM agents increasingly rely on external inference conditions: prompts, tools, memory, SOPs, skills, and harness feedback. These assets can improve task execution without changing model weights, but they are often revised by heuristic reflection or by reusing observed successes and failures as if counts alone were reliable belief. We introduce Bayesian-Agent, a native and cross-harness framework that treats reusable skills and SOPs as hypotheses about whether a frozen model will succeed under a particular prompt, context, and harness environment. Bayesian-Agent records verified trajectory evidence, maintains a feature-conditioned categorical posterior over each skill, and maps posterior state into inspectable actions such as patch, split, compress, retire, and explore. Model-facing prompts receive executable guardrails and failure-mode patches, while posterior summaries remain available for audit. With deepseek-v4-flash, incremental repair improves SOP-Bench from 80\% to 95\%, Lifelong AgentBench from 90\% to 100\%, and RealFin-Bench from 45\% to 65\%. We further evaluate Bayesian-Agent's native backend and optional GenericAgent, mini-swe-agent, and Claude Code backends. The results include positive, negative, saturated, and case-study settings, suggesting that agent skill evolution is best viewed as posterior-guided harness optimization rather than uncalibrated prompt accumulation. The source code is available at https://github.com/DataArcTech/Bayesian-Agent.