Polaris enables small LLMs to achieve recursive self-improvement by abstracting failure experiences into reusable policy patches that transfer across benchmark instances.
Examine how the policy’s logic or structure caused the error
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Polaris: A G\"odel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
Polaris enables small LLMs to achieve recursive self-improvement by abstracting failure experiences into reusable policy patches that transfer across benchmark instances.