Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

SKILL-KD: Contrastive Skill Distillation for LLM Agents

First seen · 7/30/2026, 07:27 PMLatest activity · 8/4/2026, 04:00 AM

SKILL-KD introduces contrastive skill distillation for LLM agents. It compares a student’s failed trajectory with a teacher’s trajectory on the same task, converts the actionable discrepancy into a textual skill patch, and validates the patch by rerunning the student. If failure persists, the patch is refined iteratively. The framework also maintains trace-linked edit histories and applies Drift-Aware Skill Consolidation to decide whether a patch should add, modify, delete, or skip a rule. The abstract reports consistent gains over fixed-model adaptation baselines across five agent benchmarks and two student settings.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/30, 07:27 PMnot independentRepresentative
    SKILL-KD: Contrastive Skill Distillation for LLM Agents
  2. AggregatorHuggingFace Daily Papers8/4, 04:00 AMnot independent
    SKILL-KD: Contrastive Skill Distillation for LLM Agents