4 papers
Latent Programming Horizons in Coding Agents
André Silva, Han Tu, Martin Monperrus
A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model i…
On Randomness in Agentic Evals
Bjarni Haukur Bjarnason, André Silva, Martin Monperrus
Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming…
Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces
André Silva, Gustav Thorén, Martin Monperrus
Automatic program repair seeks to generate correct code from buggy programs, with most approaches searching the correct program in a discrete, symbolic space of source code tokens.…
RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair
André Silva, Sen Fang, Martin Monperrus
Automated Program Repair (APR) has evolved significantly with the advent of Large Language Models (LLMs). Fine-tuning LLMs for program repair is a recent avenue of research, with m…