Official codebase of the paper -- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
☆330May 1, 2026Updated 6 months ago
Alternatives and similar repositories for Trace2Skill
Users that are interested in Trace2Skill are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improv…☆1,283Oct 26, 2026Updated last week
- ☆31Jun 9, 2026Updated 4 months ago
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification — COLM 2026☆83Sep 23, 2026Updated last month
- SkillX: Automatically Constructing Skill Knowledge Bases for Agents☆299Sep 3, 2026Updated 2 months ago
- [NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning☆1,032Sep 25, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"☆387Aug 12, 2026Updated 2 months ago
- CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR☆22Apr 7, 2026Updated 6 months ago
- ☆31Apr 30, 2026Updated 6 months ago
- ☆24Jun 16, 2026Updated 4 months ago
- Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills☆156Jul 27, 2026Updated 3 months ago
- ☆24Jun 16, 2026Updated 4 months ago
- Search Self-Play: Pushing the Frontier of Agent Capability without Supervision☆106Jul 23, 2026Updated 3 months ago
- SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, va…☆18,888Updated this week
- Official Implementation of Paper [NeurIPS 2026] SkillGen: Verified Inference-Time Agent Skill Synthesis☆20Sep 24, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- SkillsBench evaluates how well skills work and how effective agents are at using them.☆1,896Updated this week
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution☆609May 10, 2026Updated 5 months ago
- ☆305Jul 17, 2026Updated 3 months ago
- SkillOpt-Lite and HarnessOpt: Optimize your skill or harness with one line of vibe☆208Jul 22, 2026Updated 3 months ago
- ☆71May 20, 2026Updated 5 months ago
- ☆17Jun 13, 2026Updated 4 months ago
- SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.☆111Jul 2, 2026Updated 4 months ago
- Research artifacts from Hyra (/ˈhaɪ.rɑː/)☆190Updated this week
- [ICLR 2026] Tree Search for LLM Agent Reinforcement Learning☆410Jan 26, 2026Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆51Feb 10, 2026Updated 8 months ago
- A Unified Framework and Empirical Analysis for Long-Term Dialog Memory☆17Apr 18, 2026Updated 6 months ago
- Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-h…☆960Updated this week
- Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents☆46Apr 13, 2026Updated 6 months ago
- [NeurIPS'26] MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents☆600Oct 1, 2026Updated last month
- [ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning☆181Jan 29, 2026Updated 9 months ago
- A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Ag…☆481Oct 25, 2026Updated last week
- ☆16May 24, 2026Updated 5 months ago
- ☆17May 21, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Code for Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements☆83Sep 10, 2026Updated last month
- ☆48Nov 1, 2025Updated last year
- [ICML 2026] XSkill: Continual Learning from Experience and Skills in Multimodal Agents☆275May 13, 2026Updated 5 months ago
- ☆11Jul 27, 2026Updated 3 months ago
- Uni-Agent is a framework for training long-horizon agents.☆712Updated this week
- A version of verl to support diverse tool use [TMLR 2026]☆1,052Jul 15, 2026Updated 3 months ago
- ☆23Jul 13, 2026Updated 3 months ago