TeleTune: Evolving Agent Skills From Offline Telemetry
cs.AI, cs.CL
Submitted: 2026-10-04
Updated: 2026-10-06
Comments: Project Page: https://microsoft-teletune.github.io/
Project page: https://microsoft-teletune.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting
- SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- An Illusion of Progress? Assessing the Current State of Web Agents
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
- ExpeL: LLM Agents Are Experiential Learners
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems