LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents Paper • 2608.17393 • Published 6 days ago • 24
What Makes Interaction Trajectories Effective for Training Terminal Agents? Paper • 2606.03461 • Published Jun 2 • 3
What Makes Interaction Trajectories Effective for Training Terminal Agents? Paper • 2606.03461 • Published Jun 2 • 3
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review Paper • 2607.06065 • Published Jul 7 • 10
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review Paper • 2607.06065 • Published Jul 7 • 10
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review Paper • 2607.06065 • Published Jul 7 • 10
SWE-Review Collection SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review. Benchmark, trajectories, training data, and models for agentic code review. • 4 items • Updated May 13