Fractional coloring bounds safe merges of parallel agent edits
Verified merging keeps a 1 over fractional-chromatic-number share of local gains and cuts route wall time 15%.
Stories per day · 30 days
2 RSS
6 stories, newest first · one card per story
Stories tagged #code-repair
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
RSI-Anything uses predictive world models to recursively improve policies across code, GUI, lab, and chemistry tasks.
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
RSI-Anything uses world models to select actions and updates, improving code repair, GUI tasks, and lab planning.
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
ScienceIDE turns scientific code repositories into agent-trainable environments and trains PhAI-IDE models at 72B, 9B, and 4B scales.
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
ScienceIDE converts scientific code repositories into verifiable agent training environments, producing the PhAI-IDE 4B-72B model family.
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
A 400-task BigCodeBench evaluation shows frontier LLMs widely over-edit code; a preservation instruction cuts excess edits and raises Pass@1 by 2.3 points.