CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution Paper • 2610.10426 • Published 4 days ago • 9
CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution Paper • 2610.10426 • Published 4 days ago • 9
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published Jul 9 • 79