# SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

arXiv: https://arxiv.org/abs/2604.17308 · HTML: https://mlsanity.com/paper/2604.17308/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Builds on (most cited first, 30 of 30)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory](https://mlsanity.com/paper/2511.20857/) (2025)
- [AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution](https://mlsanity.com/paper/2603.01145/) (2026)
- [EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://mlsanity.com/paper/2603.02766/) (2026)
- [SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?](https://mlsanity.com/paper/2603.15401/) (2026)
- [XSkill: Cross Embodiment Skill Discovery](https://mlsanity.com/paper/2307.09955/) (2023)
- [Memento-Skills: Let Agents Design Agents](https://mlsanity.com/paper/2603.18743/) (2026)
- [SkillNet: Create, Evaluate, and Connect AI Skills](https://mlsanity.com/paper/2603.04448/) (2026)
- [Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM](https://mlsanity.com/paper/2403.19114/) (2024)
- [Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2601.22060/) (2026)
- [Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models](https://mlsanity.com/paper/2602.02185/) (2026)
- [SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?](https://mlsanity.com/paper/2603.00718/) (2026)
- [AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators](https://mlsanity.com/paper/2508.09101/) (2025)
- [UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision](https://mlsanity.com/paper/2601.03193/) (2026)
- [CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios](https://mlsanity.com/paper/2506.13977/) (2025)
- [DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action](https://mlsanity.com/paper/2511.22134/) (2025)
- [Coding Agents are Effective Long-Context Processors](https://mlsanity.com/paper/2603.20432/) (2026)
- [Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning](https://mlsanity.com/paper/2604.05404/) (2026)
- [Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models](https://mlsanity.com/paper/2602.10224/) (2026)

## Built on by (most cited first, 25 of 25)

- [SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution](https://mlsanity.com/paper/2605.18401/) (2026)
- [CODESKILL: Learning Self-Evolving Skills for Coding Agents](https://mlsanity.com/paper/2605.25430/) (2026)
- [EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer](https://mlsanity.com/paper/2607.05202/) (2026)
- [SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use](https://mlsanity.com/paper/2607.01874/) (2026)
- [VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation](https://mlsanity.com/paper/2606.08091/) (2026)
- [Co-Evolving Skill Generation and Policy Optimization](https://mlsanity.com/paper/2606.08755/) (2026)
- [SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents](https://mlsanity.com/paper/2606.13317/) (2026)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios](https://mlsanity.com/paper/2605.27995/) (2026)
- [From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.16621/) (2026)
- [AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?](https://mlsanity.com/paper/2608.00155/) (2026)
- [JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills](https://mlsanity.com/paper/2608.16465/) (2026)
- [OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models](https://mlsanity.com/paper/2606.16774/) (2026)
- [RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources](https://mlsanity.com/paper/2606.29538/) (2026)
- [GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks](https://mlsanity.com/paper/2608.03764/) (2026)
- [Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills](https://mlsanity.com/paper/2608.01851/) (2026)
- [SkillPoison: Progressive Skill Poisoning via Successful Experiences](https://mlsanity.com/paper/2610.07645/) (2026)
- [Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning](https://mlsanity.com/paper/2606.20002/) (2026)
- [Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents](https://mlsanity.com/paper/2607.10526/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)
- [Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents](https://mlsanity.com/paper/2609.01487/) (2026)
- [SkillAlign: Aligning Skill Interfaces for LLM-based Agents](https://mlsanity.com/paper/2609.07255/) (2026)
- [EVISKILL: Grounding Skill Evolution in Replayable Evidence](https://mlsanity.com/paper/2610.05030/) (2026)
- [EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents](https://mlsanity.com/paper/2610.13021/) (2026)
- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)

## Abstract (arXiv)

As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills, leaving open whether they can discover skills from experience, repair them after failure, and maintain a coherent library over time. We introduce SkillFlow, a benchmark of 166 tasks across 20 families in which task construction within each family follows a Domain-Agnostic Execution Flow (DAEF) that defines an agent workflow framework, allowing these tasks to share a consistent workflow. Agents are evaluated under an Agentic Lifelong Learning protocol in which they begin without skills, solve tasks sequentially within each family, externalize lessons through trajectory- and rubric-driven skill patches, and carry the updated library forward. Experiments reveal a substantial capability gap. For Claude Opus 4.6, lifelong skill evolution improves task success from 62.65% to 71.08% (+8.43 points). However, high skill usage does not necessarily imply high utility: Kimi K2.5 gains only +0.60 points despite 66.87% skill usage, while Qwen-Coder-Next reaches only a 44.58% task completion rate and still regresses relative to the vanilla setting. SkillFlow contributes a structured testbed for this direction and an in-depth empirical analysis of skill discovery, patching, transfer, and their failure modes under lifelong evaluation.