COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.

The paper proposes Skill-Conditioned Gated Self-Distillation (SGSD), a novel framework that uses retrieved, potentially noisy skills to guide LLM reasoning, achieving state-of-the-art performance on m…

This paper proposes a method for creating scalable browser agents by cloning user interaction skills from human browsing data using natural language skills and a skill graph.

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes a…

This paper investigates the phenomenon of 'copying' in Distribution Matching Distillation (DMD), finding that high-dimensional distillation causes student models to spontaneously reproduce the teacher…

The paper proposes a novel layer and point-wise projection mapping combined with LoRA injection to efficiently distill knowledge from a large teacher model to a small student model, significantly impr…

This paper introduces SkillComposer, a method for structured skill composition in LLM agents, which predicts an executable skill plan that jointly specifies the activated subset, count, and execution…

The paper introduces Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks…

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

The paper introduces Trust-Region behavior Blending (TRB), a warmup method that improves on-policy distillation by replacing poor early student rollouts with teacher-aligned behavior policies, leading…

The paper introduces a systematic framework to convert large Mixture-of-Experts (MoE) models into memory-efficient, fully dense architectures, achieving superior performance compared to traditional pr…

The paper proposes Multi-Teacher Bayesian Knowledge Distillation (MT-BKD), a framework that uses Bayesian inference and teacher-informed priors to improve model compression, enhance predictive accurac…

SkillTrojan introduces a novel backdoor attack targeting the composition of reusable skills in agent systems, demonstrating high attack success rates with minimal impact on normal system functionality…

This paper measures the impact of procedural skills on LLM agents, distinguishing between improvements and regressions, and identifies causes of regression.

The paper proposes Distribution-Aligned Self-Distillation (DASD) to improve self-distillation by dynamically filtering high-perplexity tokens, thereby preserving useful logical knowledge while suppres…

The paper introduces Lookahead Group Reward (&) to combat Supervision Fidelity Decay (SFD) in on-policy distillation, significantly improving student model performance on long reasoning tasks.

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

The paper introduces Lossless Anti-Distillation Sampling (LADS), a novel sampling scheme that makes harvested data correlated for malicious distillers while ensuring benign users receive statistically…

The paper identifies a linear predictive law linking the initial performance gap in on-policy self-distillation (OPSD) to the final performance improvement, allowing researchers to anticipate and tune…