小模型通过经验抽象实现自我修复，持续提升推理能力。
Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
- 用经验抽象将失败转化为可复用的策略，进行政策级修复。
- 70亿参数模型在多个评测集上表现超越基线，提升稳定。
- 适合关注小模型自我进化与可解释修复的研究者使用。
Gödel智能体实现递归自我改进：智能体审视自身策略并追踪错误后，在测试循环中修改策略。我们提出Polaris，一种针对紧凑模型的Gödel智能体框架，通过经验抽象实现策略修复，将失败转化为策略更新，形成分析、策略制定、抽象和最小代码修补的结构化循环，并加入保守检查。与响应级修正或参数调优不同，Polaris进行策略级修改，生成小型、可审计的补丁，这些补丁可持久保留并在每个基准测试的未见实例中复用。在循环中，智能体开展元推理：解释错误，提出具体策略修订，并更新策略。为实现累积性策略优化，我们引入经验抽象，将失败提炼为紧凑且可复用的策略，可在未见实例间迁移。配备Polaris的70亿参数模型在MGSM、DROP、GPQA和LitBench（涵盖算术推理、组合推理、研究生级问题求解及创意写作评估）上，持续优于基础策略和竞争性基线。
原文摘要 · Abstract (English)
Gödel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, Gödel agent for compact models that performs policy repair via experience abstraction, turning failures into policy updates through a structured cycle of analysis, strategy formation, abstraction, and minimal code patch repair with conservative checks. Unlike response level self correction or parameter tuning, Polaris makes policy level changes with small, auditable patches that persist in the policy and are reused on unseen instances within each benchmark. As part of the loop, the agent engages in meta reasoning: it explains its errors, proposes concrete revisions to its own policy, and then updates the policy. To enable cumulative policy refinement, we introduce experience abstraction, which distills failures into compact, reusable strategies that transfer to unseen instances. On MGSM, DROP, GPQA, and LitBench (covering arithmetic reasoning, compositional inference, graduate-level problem solving, and creative writing evaluation), a 7-billion-parameter model equipped with Polaris achieves consistent gains over the base policy and competitive baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。