Polaris introduces a 'Gödel Agent' framework that allows 7B-parameter models to recursively improve their own policies through auditable code patches.
March 25, 2026
Original Paper
Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
arXiv · 2603.23129
The Takeaway
Unlike standard self-correction which happens at the response level, this framework enables persistent, cumulative policy refinement. It demonstrates that smaller, compact models can perform autonomous strategy abstraction and self-repair previously reserved for much larger systems.
From the 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 le