Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Paper • 2610.20344 • Published • 106
Christian Krause
christiankrause
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents updated a model 15 days ago
christiankrause/dl-classification published a model 15 days ago
christiankrause/dl-classificationOrganizations
None yet
upvoted a paper 3 days ago
upvoted 3
papers 15 days ago
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 565
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Paper • 2609.36585 • Published • 73
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 665