PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards
PreciseCoder trains code models to debug with smaller, localized edits instead of hallucinating bugs.
3 stories, newest first · one card per story
PreciseCoder trains code models to debug with smaller, localized edits instead of hallucinating bugs.
Executable checks slightly improve LLM scientific-coding agents' program repair versus written requirements on SciCode.
AdaRepair-Mem introduces coverage-, quality-, and stage-aware memory retrieval that improves LLM-based repository-level program repair on SWE-Bench.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views