Pith. sign in

REVIEW 15 cited by

Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software 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 2411.00622 v1 pith:HZS3UGSO submitted 2024-11-01 cs.SE cs.AI

Yingwei Ma , Rongyu Cao , Yongchang Cao , Yue Zhang , Jue Chen , Yibo Liu , Yuchen Liu , Binhua Li
show 2 more authors
Fei Huang Yongbin Li
This is my paper · ORCID
classification cs.SEcs.AI
keywords softwarelingmaswe-gptimprovementmodelsprocessescodeissues
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent advancements in LLM-based agents have led to significant progress in automatic software engineering, particularly in software maintenance and evolution. Despite these encouraging advances, current research faces two major challenges. First, SOTA performance primarily depends on closed-source models, which significantly limits the technology's accessibility, and potential for customization in diverse SE tasks. Second, these models are predominantly trained on static code data, lacking a deep understanding of the dynamic interactions, iterative problem-solving processes, and evolutionary characteristics inherent in software development. To address these challenges, our study adopts a software engineering perspective. We recognize that real-world software maintenance and evolution processes encompass not only static code data but also developers' thought processes, utilization of external tools, and the interaction between different functional personnel. Consequently, we introduce the Lingma SWE-GPT series, comprising Lingma SWE-GPT 7B and 72B. By learning from and simulating real-world code submission activities, Lingma SWE-GPT systematically incorporates the dynamic interactions and iterative problem-solving inherent in software development process, thereby achieving a more comprehensive understanding of software improvement processes. We conducted experimental evaluations using SWE-bench Verified benchmark. The results demonstrate that Lingma SWE-GPT 72B successfully resolves 30.20% of the GitHub issues, marking a significant improvement in automatic issue resolution (22.76% relative improvement compared to Llama 3.1 405B), approaching the performance of closed-source models (31.80\% issues of GPT-4o resolved). Notably, Lingma SWE-GPT 7B resolves 18.20% of the issues, highlighting the potential for applying smaller models to ASE tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 15 Pith papers

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

  1. MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

    cs.SE 2026-07 accept novelty 7.0 of 10

    Distilling 1,001 whole-life-cycle source-free program-synthesis trajectories into Qwen3.6-27B raises ProgramBench pass rate from 37.98% to 49.51% and transfers to seven unseen SE benchmarks.

  2. Evaluating LLM Agents on Automated Software Analysis Tasks

    cs.SE 2026-04 unverdicted novelty 7.0 of 10

    A purpose-built, staged LLM agent correctly sets up and executes software analysis tools on 33 of 35 benchmark tasks, outperforming general-purpose agent baselines by at least 17 percentage points.

  3. SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories

    cs.SE 2025-09 conditional novelty 7.0 of 10

    A pipeline that mirrors real GitHub issues into existing test environments of other repositories, producing over 60,000 verifiable issue-resolving tasks that improve code-agent training.

  4. WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

    cs.CL 2025-05 conditional novelty 7.0 of 10

    WebGen-Bench provides 101 website-building tasks with 647 atomic test cases, and a trained Qwen2.5-Coder-32B model reaches 38.2% accuracy, outperforming DeepSeek-R1's 27.8%.

  5. Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework

    cs.SE 2026-08 conditional novelty 6.0 of 10

    RETRACE improves coding-agent patch correctness by having the model guess the problem a patch solves without seeing the original report, then reconciling that guess with the report to decide whether to submit or revise.

  6. From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair

    cs.SE 2026-01 conditional novelty 6.0 of 10

    Backward reasoning distilled from a repository's already-fixed issues, injected as prompts, lifts LLM repair success on SWE-Bench Lite by up to 10.4 Pass@1 points.

  7. SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

    cs.SE 2025-07 conditional novelty 6.0 of 10

    A competitive multi-agent debate over graph-derived fault propagation chains lifts automated issue resolution on SWE-bench Verified to 41.4% pass@1.

  8. Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A 32B model trained to self-evolve patch candidates through RL reaches 41.6% on SWE-Bench Verified with 50 samples, comparable to a 70B model using 500 samples.

  9. Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks

    cs.SE 2025-05 conditional novelty 6.0 of 10

    A graph-integrated open-source LLM with agentless RAG resolves 43% of SWE-bench Lite issues, best among open-weight models.

  10. PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification

    cs.RO 2025-02 conditional novelty 6.0 of 10

    A rule-based LLM patching agent with a refinement loop resolves 45.3% and 53.6% on SWE-bench Lite and Verified for about $1 per instance, beating open-source baselines.

  11. LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues

    cs.SE 2024-11 conditional novelty 6.0 of 10

    A reflection-based experience pool raises LLM issue reproduction accuracy from 45% to 54% on SWE-bench Lite, with gains in downstream issue resolving.

  12. SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

    cs.CL 2025-01 conditional novelty 5.0 of 10

    An open-source two-module pipeline (retriever plus editor) trained on 110K GitHub issue patches reaches 30.2% on SWE-Bench Verified and 24.7% on Lite with P2P filtering.

  13. Position: Intelligent Coding Systems Should Write Programs with Justifications

    cs.SE 2025-08 conditional novelty 4.0 of 10

    A position paper advocating that intelligent coding systems should accompany code with justified explanations that are cognitively aligned and semantically faithful.

  14. Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents

    cs.SE 2025-05 conditional novelty 4.0 of 10

    Guided by a learned value critic, 1-step lookahead and trajectory selection lift an open-weights SWE agent to 40.8% on SWE-bench Verified, roughly doubling its success rate.

  15. Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey

    cs.LG 2025-05 unverdicted novelty 2.0 of 10

    A survey that organizes LLM-based complex problem solving into three components, multi-step reasoning, domain knowledge, and result verification, and reviews methods and challenges across four application domains.

Pith tools