SKILL-KD：面向LLM智能體的對比技能蒸餾

摘要

基於技能的提示已成為提升大型語言模型（LLM）智能體的實用機制，然而現有的技能獲取方法往往將技能視為經驗總結、記憶條目或成功示範的直接摘要。這對較弱的學生智能體造成了不匹配：當學生因缺乏任務知識或操作策略而失敗時，其失敗軌跡可能不足以提供推斷缺失行為的證據，而教師軌跡則可能過於隱晦，難以內化為可重複使用的指導。我們提出 SKILL-KD，一個對比式技能蒸餾框架，將技能視為不同能力智能體之間的明確蒸餾媒介。針對同一任務中學生的失敗與教師軌跡，SKILL-KD 將兩者之間可行動的差異蒸餾為文字技能補丁，透過重新執行學生來評估該補丁，並在學生仍失敗時迭代精煉補丁。為防止重複的局部更新造成技能漂移，SKILL-KD 進一步維護軌跡連結的編輯歷史，並執行漂移感知技能整合，判斷每個補丁應新增新規則、刪除或修改既有規則，還是予以跳過。在五個智能體基準測試與兩種學生設定下，SKILL-KD 持續優於固定模型適應基線，提升凍結學生智能體的表現。

English

Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summaries of successful demonstrations. This creates a mismatch for weaker student agents: when a student fails because it lacks task knowledge or operational strategy, its failed trajectory may not contain enough evidence to infer the missing behavior, while the teacher trajectory may be too implicit to be internalized as reusable guidance. We propose SKILL-KD, a contrastive skill distillation framework that treats skills as an explicit distillation medium between agents of different capabilities. Given a student failure and the teacher trajectory on the same task, SKILL-KD distills their actionable discrepancy into a textual skill patch, evaluates the patch by re-running the student, and iteratively refines the patch when the student still fails. To prevent repeated local updates from causing skill drift, SKILL-KD further maintains trace-linked edit histories and performs Drift-Aware Skill Consolidation, deciding whether each patch should add a new rule, delete or modify an existing rule, or be skipped. Across five agent benchmarks and two student settings, SKILL-KD consistently improves frozen student agents over fixed-model adaptation baselines.