REVIEW 7 cited by
MASAI: Modular Architecture for Software-engineering AI Agents
Not yet reviewed by Pith; the record is open.
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
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.
Forward citations
Cited by 7 Pith papers
-
IssueExec: A Test-Driven Approach for Localizing Software Engineering Issues
IssueExec localizes issue-relevant code by retrieving related tests and following their execution traces, beating prior localization methods on SWE-bench Lite.
-
Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows
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.
-
From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
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.
-
Git Context Controller: Manage the Context of LLM-based Agents like Git
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.
-
TN-AutoRCA: Benchmark Construction and Agentic Framework for Self-Improving Alarm-Based Root Cause Analysis in Telecommunication Networks
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.
-
Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
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.
-
Self-Evolving Coding Agents
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.
Discussion (0). Continue with ORCID to comment.