# SemAgent: A Semantics Aware Program Repair Agent

arXiv: https://arxiv.org/abs/2506.16650 · HTML: https://mlsanity.com/paper/2506.16650/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 6 of 6)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Unit Test Case Generation with Transformers and Focal Context](https://mlsanity.com/paper/2009.05617/) (2020)
- [SpecRover: Code Intent Extraction via LLMs](https://mlsanity.com/paper/2408.02232/) (2024)
- [Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM](https://mlsanity.com/paper/2402.00097/) (2024)

## Built on by (most cited first, 9 of 9)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks](https://mlsanity.com/paper/2511.00872/) (2025)
- [Beyond the Prompt: An Empirical Study of Cursor Rules](https://mlsanity.com/paper/2512.18925/) (2025)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [EviACT: An Evidence-to-Action Framework for Agentic Program Repair](https://mlsanity.com/paper/2605.27238/) (2026)
- [Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review](https://mlsanity.com/paper/2605.17548/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs](https://mlsanity.com/paper/2607.26591/) (2026)
- [TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry](https://mlsanity.com/paper/2610.04981/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown impressive capabilities in downstream software engineering tasks such as Automated Program Repair (APR). In particular, there has been a lot of research on repository-level issue-resolution benchmarks such as SWE-Bench. Although there has been significant progress on this topic, we notice that in the process of solving such issues, existing agentic systems tend to hyper-localize on immediately suspicious lines of code and fix them in isolation, without a deeper understanding of the issue semantics, code semantics, or execution semantics. Consequently, many existing systems generate patches that overfit to the user issue, even when a more general fix is preferable. To address this limitation, we introduce SemAgent, a novel workflow-based procedure that leverages issue, code, and execution semantics to generate patches that are complete - identifying and fixing all lines relevant to the issue. We achieve this through a novel pipeline that (a) leverages execution semantics to retrieve relevant context, (b) comprehends issue-semantics via generalized abstraction, (c) isolates code-semantics within the context of this abstraction, and (d) leverages this understanding in a two-stage architecture: a repair stage that proposes fine-grained fixes, followed by a reviewer stage that filters relevant fixes based on the inferred issue-semantics. Our evaluations show that our methodology achieves a solve rate of 44.66% on the SWEBench-Lite benchmark beating all other workflow-based approaches, and an absolute improvement of 7.66% compared to our baseline, which lacks such deep semantic understanding. We note that our approach performs particularly well on issues requiring multi-line reasoning (and editing) and edge-case handling, suggesting that incorporating issue and code semantics into APR pipelines can lead to robust and semantically consistent repairs.