Pith. sign in

REVIEW 12 cited by

MASAI: Modular Architecture for Software-engineering AI Agents

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 2406.11638 v1 pith:DQUIAG7H submitted 2024-06-17 cs.AI cs.SE

Daman Arora , Atharv Sonwane , Nalin Wadhwa , Abhav Mehrotra , Saiteja Utpala , Ramakrishna Bairi , Aditya Kanade , Nagarajan Natarajan This is my paper · ORCID
classification cs.AIcs.SE
keywords masaiarchitecturedifferentmodularsub-agentsachieveagentsobjectives
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, where different LLM-powered sub-agents are instantiated with well-defined objectives and strategies tuned to achieve those objectives. Our modular architecture offers several advantages: (1) employing and tuning different problem-solving strategies across sub-agents, (2) enabling sub-agents to gather information from different sources scattered throughout a repository, and (3) avoiding unnecessarily long trajectories which inflate costs and add extraneous context. MASAI enabled us to achieve the highest performance (28.33% resolution rate) on the popular and highly challenging SWE-bench Lite dataset consisting of 300 GitHub issues from 11 Python repositories. We conduct a comprehensive evaluation of MASAI relative to other agentic methods and analyze the effects of our design decisions and their contribution to the success of MASAI.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. IssueExec: A Test-Driven Approach for Localizing Software Engineering Issues

    cs.SE 2026-07 conditional novelty 6.0 of 10

    IssueExec localizes issue-relevant code by retrieving related tests and following their execution traces, beating prior localization methods on SWE-bench Lite.

  2. Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows

    cs.SE 2026-07 conditional novelty 6.0 of 10

    A three-agent LLM workflow plus a test-specialized knowledge graph generates unit tests that beat prior LLM and search-based tools on coverage and mutation score.

  3. 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.

  4. Git Context Controller: Manage the Context of LLM-based Agents like Git

    cs.SE 2025-07 reject novelty 6.0 of 10

    GCC, a Git-inspired context management layer, is reported to lift a Claude-based agent to 48.00% on SWE-Bench-Lite and to enable a self-replicating CLI that resolves 40.7% of tasks versus 11.7% without it.

  5. TN-AutoRCA: Benchmark Construction and Agentic Framework for Self-Improving Alarm-Based Root Cause Analysis in Telecommunication Networks

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A new 530-scenario benchmark for telecom alarm root cause analysis, plus an iterative agent that lifts F1 from 58.99% to 91.79% by repeatedly repairing its code against the benchmark.

  6. Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study

    cs.SE 2025-06 accept novelty 6.0 of 10

    An empirical study of five LLM-based program repair agents shows they excel on simple fixes but overfit tests and struggle with test generation, regression selection, and advanced tooling.

  7. OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution

    cs.SE 2025-05 conditional novelty 6.0 of 10

    OmniGIRL introduces a 959-instance multilingual, multimodal GitHub issue resolution benchmark; the best result, GPT-4o with Agentless-X, resolves only 8.6% of issues.

  8. kAgent: An execution-guided crash resolution agent for the Linux kernel

    cs.SE 2025-04 reject novelty 6.0 of 10

    An LLM agent with execution-trace-guided hypothesis generation resolves about 65% of fuzzed Linux kernel crashes when told which file to fix, but most of its 'fixed' crashes are resolved by deleting or bypassing code.

  9. 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.

  10. AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions

    cs.SE 2024-11 conditional novelty 6.0 of 10

    AEGIS combines concise context extraction with finite-state-machine feedback control to make LLM agents reproduce more software bugs from issue descriptions than existing baselines.

  11. Human-In-the-Loop Software Development Agents

    cs.SE 2024-11 conditional novelty 5.0 of 10

    A deployed human-in-the-loop LLM agent framework at Atlassian JIRA achieved 82% plan approval but only 25% of generated code became pull requests, with code quality cited as a key challenge.

  12. 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.

Pith tools