MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution

Paper recorded by Signals 4 on 2026-11-03 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-03 on arXiv · recorded by Signals 4 on 2026-11-04

Category: cs.CL · 自然语言处理 · first seen 2026-11-04

Abstract

Skill memories encode past experiences as textual prompts to improve reinforcement learning (RL) for self-evolving agents. Complementing RL, On-Policy Self-Distillation (OPSD) provides dense, fine-grained supervision to internalize knowledge from skill-guided trajectories and accelerate policy learning. However, self-generated memories often contain noisy supervision and functionally entangled, re

Read on arXiv →