The authors designed two tasks that require explicit reasoning about runtime program states.
Training models on runtime program-state reasoning boosts automated software engineering
Comet-9B, a 9-billion-parameter model, achieves competitive performance on patch generation, regression-test generation, and security proof-of-concept generation after supervised fine-tuning and reinforcement learning on two novel reasoning tasks.
Big Tech
Hongwei Li · Spandan Garg · Yufan Huang
University of California, Santa Barbara · Microsoft
Research Digest··3 min read
The authors introduce two complementary program-state reasoning tasks—buggy input-output reasoning and precondition-postcondition reasoning—and incorporate them into a staged post-training pipeline to build Comet-9B, a 9B-parameter language model.
Why this paper
From Microsoft and University of California, Santa Barbara
In one line
Training LLMs to reason about runtime program states improves repository-level patch generation, test generation, and security PoC generation.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (3 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§