RepairAgent autonomously repairs 164 bugs on Defects4J including 39 not fixed by prior techniques by treating an LLM as an agent that invokes tools via a finite state machine and dynamic prompts.
Cigar: Cost-efficient program repair with llms
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.SE 4roles
background 3polarities
background 3representative citing papers
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.
Ditto quantizes Code LLMs with per-block K-Means codebooks and compiles GEMV into BLAS calls, claiming up to 10.5× faster, 6.4× leaner local inference with ~0.27% pass@1 loss.
A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.
citing papers explorer
-
RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
RepairAgent autonomously repairs 164 bugs on Defects4J including 39 not fixed by prior techniques by treating an LLM as an agent that invokes tools via a finite state machine and dynamic prompts.
-
Agentless: Demystifying LLM-based Software Engineering Agents
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.
-
Compiling Code LLMs into Lightweight Executables
Ditto quantizes Code LLMs with per-block K-Means codebooks and compiles GEMV into BLAS calls, claiming up to 10.5× faster, 6.4× leaner local inference with ~0.27% pass@1 loss.
-
Large Language Model-Based Agents for Software Engineering: A Survey
A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.