Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents
Paper • 2610.33568 • Published • 369
David Finch
davidf419
AI & ML interests
Custom harnesses, MCP servers, trying coding+vision finetunes on 16gb vram.
Recent Activity
liked a model about 18 hours ago
microsoft/Mage-VL-Cowork reacted to danielhanchen's post with 👍 1 day ago
Your local LLM can now take control of a browser and complete tasks autonomously via Unsloth!
Qwen3.8-27B successfully controlled the browser to complete tasks like chess, painting, with no human intervention.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/browser-use liked a model 1 day ago
LiquidAI/LFM3-Omni-2BOrganizations
None yet
upvoted a paper 4 days ago
upvoted a paper 9 days ago
upvoted 6
papers 10 days ago
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
Paper • 2607.17977 • Published • 120
SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
Paper • 2609.37539 • Published • 14
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Paper • 2607.28568 • Published • 184
WorkGenesis: Building the Worlds That Teach Agents to Work
Paper • 2609.39325 • Published • 2
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
Paper • 2609.11977 • Published • 124
Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents
Paper • 2609.33772 • Published • 37