PAIR-Bench defines a progressive hinting protocol with failure-region and hint-depth controls to measure LLM code refinement trajectories in detail.
Is the cure worse than the disease? overfitting in automated program repair,
2 Pith papers cite this work, alongside 324 external citations. Polarity classification is still indexing.
2
Pith papers citing it
324
external citations · external index
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
P2T distills reference patches into a latent process graph and uses it to select shortest effective trajectory segments from teacher rollouts, yielding up to 10.8 point Pass@1 gains on SWE-bench Verified with 15% lower inference cost using only 1.8k instances.
citing papers explorer
-
Benchmarking Code Improvement with Progressive, Adaptive, and Interactive Feedback
PAIR-Bench defines a progressive hinting protocol with failure-region and hint-depth controls to measure LLM code refinement trajectories in detail.
-
From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
P2T distills reference patches into a latent process graph and uses it to select shortest effective trajectory segments from teacher rollouts, yielding up to 10.8 point Pass@1 gains on SWE-bench Verified with 15% lower inference cost using only 1.8k instances.