Hypothesis-Driven Skill Optimization for LLM Agents

2026-06-21

AI Summary

This work addresses the vulnerability of external skill updating to sparse or noisy execution trajectories, which can lead to the entrenchment of ineffective or even detrimental policies. To mitigate this issue, the authors propose a training-free skill optimization framework that leverages a falsifiable hypothesis-driven mechanism. By integrating controlled experiments, behavioral discrepancy analysis, and progressive skill disclosure, the method enables auditable and noise-resilient skill curation and execution at frozen model inference endpoints. Evaluated on ALFWorld, the approach yields substantial performance gains: average success rates improve by 6.9 and 4.0 percentage points for Qwen3-8B and Qwen3.6-27B, respectively. Notably, it maintains a +7.1-point advantage even under 20% erroneous feedback and demonstrates strong cross-run and cross-model transferability.

Abstract

External skills can improve action-oriented LLM agents without changing model weights, but persistent skill updates are risky when they are distilled from sparse or noisy trajectories. A plausible reflection may encode a useful procedure, a spurious shortcut, or a rule that the target executor cannot reliably follow. We propose Hypothesis-Driven Skill Optimization (HDSO), a train-free framework in which both the skill curator and the agent executor are frozen inference endpoints. The curator observes executor traces, proposes a falsifiable hypothesis with an explicit validation plan, instantiates the hypothesis as a candidate skill package, validates the package through paired control/treatment executions, reviews behavior differences, and consolidates only supported candidates into an approved repository. The executor consumes approved skills through progressive disclosure, preserving the executor-only path when no skill is selected. On ALFWorld, HDSO improves executor-only baselines by +6.9 Avg. SR points for Qwen3-8B and +4.0 points for Qwen3.6-27B. Under 20% randomly flipped success/failure feedback during skill discovery and validation, HDSO preserves a +7.1-point gain for Qwen3-8B. Transfer and heterogeneous-pair diagnostics further show that validated repositories can be useful beyond the run that produced them, but cross-model curation succeeds only when curator diagnosis, executor capability, and validation evidence align. HDSO provides an auditable skill lifecycle for frozen action agents rather than an unconstrained memory accumulation procedure.

Problem

• LLM agents
• skill optimization
• hypothesis-driven
• frozen models
• reliable skill updating

Innovation

• Hypothesis-Driven Skill Optimization
• frozen LLM agents
• skill validation
• train-free framework
• auditable skill lifecycle