Analysis of 13 coding agent scaffolds at pinned commits yields a 12-dimension taxonomy showing five composable loop primitives, with 11 agents combining multiple primitives instead of using one fixed structure.
Masai: Modular architecture for software-engineering ai agents,
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
Debug2Fix integrates interactive debugging via subagents into coding agents, delivering >20% gains on GitBug-Java and SWE-Bench-Live while enabling weaker models to match stronger ones.
The first empirical study of test overfitting shows that auto-generated tests from issues can lead to code that passes observed tests but misses important cases or breaks functionality in SWE-bench issue resolution.
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.
AI-assisted task splitting creates more granular and complete task lists than traditional methods alone but requires human oversight to remove irrelevant suggestions, with participants favoring hybrid workflows.
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.
S-AI-Recursive operationalizes reasoning as a closed-loop hormonal iteration with Clarifine and Confusionin to reach stable equilibrium, achieving competitive benchmark performance with under 10 million parameters via temporal depth instead of width.
citing papers explorer
-
Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
Analysis of 13 coding agent scaffolds at pinned commits yields a 12-dimension taxonomy showing five composable loop primitives, with 11 agents combining multiple primitives instead of using one fixed structure.
-
Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?
Debug2Fix integrates interactive debugging via subagents into coding agents, delivering >20% gains on GitBug-Java and SWE-Bench-Live while enabling weaker models to match stronger ones.
-
Investigating Test Overfitting on SWE-bench
The first empirical study of test overfitting shows that auto-generated tests from issues can lead to code that passes observed tests but misses important cases or breaks functionality in SWE-bench issue resolution.
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
-
Agentless: Demystifying LLM-based Software Engineering Agents
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.
-
Splitting User Stories Into Tasks with AI -- A Foe or an Ally?
AI-assisted task splitting creates more granular and complete task lists than traditional methods alone but requires human oversight to remove irrelevant suggestions, with participants favoring hybrid workflows.
-
Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.
-
S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning
S-AI-Recursive operationalizes reasoning as a closed-loop hormonal iteration with Clarifine and Confusionin to reach stable equilibrium, achieving competitive benchmark performance with under 10 million parameters via temporal depth instead of width.