FRAMES evolves an LLM agent's skill files from policy and feedback using consensus-filtered proposals, a per-category non-regression gate, and Pareto selection over accuracy and cost; it reports leading accuracy-cost results on FinDAS and tau-bench.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows
FRAMES evolves an LLM agent's skill files from policy and feedback using consensus-filtered proposals, a per-category non-regression gate, and Pareto selection over accuracy and cost; it reports leading accuracy-cost results on FinDAS and tau-bench.