Research

Paper

TESTING March 24, 2026

Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

Authors

Aditya Kakade, Vivek Srivastava, Shirish Karande

Abstract

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, a 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 pat ch 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.

Metadata

arXiv ID: 2603.23129
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23129v1</id>\n    <title>Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair</title>\n    <updated>2026-03-24T12:25:32Z</updated>\n    <link href='https://arxiv.org/abs/2603.23129v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23129v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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, a 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 pat ch 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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-24T12:25:32Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Aditya Kakade</name>\n    </author>\n    <author>\n      <name>Vivek Srivastava</name>\n    </author>\n    <author>\n      <name>Shirish Karande</name>\n    </author>\n  </entry>"
}