Pith. sign in

REVIEW 16 cited by

AutoCodeRover: Autonomous Program Improvement

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.05427 v3 pith:TNL3FO2G submitted 2024-04-08 cs.SE cs.AI

Yuntong Zhang , Haifeng Ruan , Zhiyu Fan , Abhik Roychoudhury This is my paper
classification cs.SEcs.AI
keywords softwareprogramautocoderovercodeefficacyengineeringgithubimprovement
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Researchers have made significant progress in automating the software development process in the past decades. Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding. Nevertheless, software engineering involves the process of program improvement apart from coding, specifically to enable software maintenance (e.g. bug fixing) and software evolution (e.g. feature additions). In this paper, we propose an automated approach for solving GitHub issues to autonomously achieve program improvement. In our approach called AutoCodeRover, LLMs are combined with sophisticated code search capabilities, ultimately leading to a program modification or patch. In contrast to recent LLM agent approaches from AI researchers and practitioners, our outlook is more software engineering oriented. We work on a program representation (abstract syntax tree) as opposed to viewing a software project as a mere collection of files. Our code search exploits the program structure in the form of classes/methods to enhance LLM's understanding of the issue's root cause, and effectively retrieve a context via iterative search. The use of spectrum-based fault localization using tests, further sharpens the context, as long as a test-suite is available. Experiments on SWE-bench-lite (300 real-life GitHub issues) show increased efficacy in solving GitHub issues (19% on SWE-bench-lite), which is higher than the efficacy of the recently reported SWE-agent. In addition, AutoCodeRover achieved this efficacy with significantly lower cost (on average, $0.43 USD), compared to other baselines. We posit that our workflow enables autonomous software engineering, where, in future, auto-generated code from LLMs can be autonomously improved.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality

    cs.SE 2026-07 conditional novelty 7.5 of 10

    Across 35 Qwen Code releases with a fixed LLM, resolve rates do not significantly improve while token use and tool calls roughly double, driven by feature-heavy releases and high-risk components.

  2. LoopsBench: From Harness Engineering to Loop Engineering in Benchmarking Coding Agent

    cs.SE 2026-07 conditional novelty 7.0 of 10

    LoopsBench exposes coding agents to dependency-DAG tasks with regression obligations; the best configuration, Opus-4.7 with Claude Code and outer continuation, resolves 25.00% of tasks.

  3. Preventing Premature Commitment in Coding Agents with an Evidence-Conditioned Execution Layer

    cs.SE 2026-07 conditional novelty 7.0 of 10

    ECLoop gates coding agents' commit actions on task-specific evidence conditions, raising SWE-bench Verified Pass@1 by 4.8-11.8 points without retraining or scaffold changes.

  4. Semantic Drift in Bug Resolution: How Behavioral Signals Propagate from Reports to Tests and Patches

    cs.SE 2026-07 conditional novelty 7.0 of 10

    Behavioral signals in bug reports propagate only partially into tests and fixes; alignment is measurable but representation-dependent, and LLM judges are systematically optimistic versus human ratings.

  5. LLM Agents Can See Code Repositories

    cs.SE 2026-06 unverdicted novelty 7.0 of 10

    Visual graphs of repository structure added to text inputs for multimodal LLM agents reduce token consumption by up to 26% while maintaining or improving issue-resolution accuracy.

  6. When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation

    cs.SE 2026-07 conditional novelty 6.5 of 10

    Code-only tool surfaces beat or match the cheapest tool-rich rival on cost in three of four (regime, agent) cells at matched pass rates; Claude on SWE-bench is the directional exception via failure cost.

  7. Shared Organizational Memory for Enterprise Coding Agents: System Design and Deployment Snapshot

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A production deployment snapshot shows hook-based automatic capture and LLM curation turning 900 agent learnings into 1,144 shared question-answer memories, with no evidence yet of retrieval or coding-task benefit.

  8. SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization

    cs.AI 2026-07 conditional novelty 6.0 of 10

    SCOPE evolves LLM-generated auxiliary objective functions and selects a validated portfolio of them to guide fixed combinatorial search engines under strict black-box query budgets.

  9. Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback

    cs.SE 2025-07 conditional novelty 6.0 of 10

    Meta's Engineering Agent solved 42.3% of curated internal test-failure tasks offline and landed 25.5% of generated fixes in production over three months.

  10. Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details

    cs.AI 2026-08 conditional novelty 5.0 of 10

    For Other-Play in Yokai, agents trained with different implementation details coordinate across implementations about as well as across seeds, supporting inter-seed cross-play as a proxy for cross-implementation evaluation.

  11. Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A design and open-source implementation of a filesystem layer that persists Claude Code agent-team state to disk, enabling checkpointing, recovery, and cross-session communication.

  12. ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair

    cs.AI 2026-07 unverdicted novelty 5.0 of 10

    ContextSniper reduces token use by 38.9-51.5% in repository-level program repair agents on SWE-bench Lite with 2 percentage point drops in resolution rate.

  13. Detection Time Distribution Predicted Using Absorbing Boundary Conditions and Imaginary Potentials

    quant-ph 2026-03 unverdicted novelty 5.0 of 10

    Three inequivalent quantum detection-time proposals yield waveguide arrival distributions showing partial reflection, spin-orientation independence (for tested parameters), and width dependence when spin couples to th...

  14. CoRet: Improved Retriever for Code Editing

    cs.LG 2025-05 conditional novelty 5.0 of 10

    CoRet fine-tunes a code encoder with a repository-level likelihood loss and call-graph context, improving retrieval recall on SWE-bench and Long Code Arena.

  15. Self-Evolving Coding Agents

    cs.SE 2026-08 conditional novelty 4.0 of 10

    A systematic survey that defines self-evolving coding agents, organizes systems into a five-category object-centered taxonomy, and analyzes when and on what evidence these agents evolve.

  16. Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles

    cs.SE 2025-06 conditional novelty 4.0 of 10

    Repeton, a retrieval-free, fully open-source LLM agent, fixes 11.67% of SWE-bench Lite bugs through iterative structured patch-and-test cycles.

Pith tools