伊藤拓海

isabellat71's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 5 hours ago

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Paper • 2606.12344 • Published 1 day ago • 55

upvoted a paper 1 day ago

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published 7 days ago • 51

upvoted a paper 2 days ago

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Paper • 2606.03988 • Published 9 days ago • 115

upvoted 2 papers 8 days ago

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Paper • 2606.01311 • Published 12 days ago • 36

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published 15 days ago • 192