The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
Llm-based multi-agent systems for software engineering: Literature review, vision and the road ahead
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative 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.
Terminus-4B, a Qwen3-4B post-trained with SFT and rubric-based GRPO, matches or beats frontier models as a terminal-execution subagent while cutting main-agent tokens ~30% on SWE-Bench-style tasks.
APIKG4Syn synthesizes API-oriented training data via knowledge graphs and Monte Carlo search to fine-tune a 7B model that reaches 25% pass@1 on HarmonyOS code generation, beating untuned GPT-4o at 17.59%.
Systematic review of agentic AI in the SDLC finds output verifiability drives industrial adoption in later phases, with Planner-Executor-Reviewer as the dominant pattern, plus a new multi-agent LLM screening pipeline for high-volume SLRs.
A case study of iterative auditing on AEGIS LLM multi-agent specs found 51 defects over nine rounds with non-monotonic convergence, a post-hoc seven-category taxonomy, and replications showing category kappa of 0.80.
FormIDEAble models human-agent cooperation as a Priced Timed Markov Decision Process and solves cost-bounded reachability to produce socially-aware strategies with safety guarantees, shown in an evacuation example.
Qualitative interview study of 16 practitioners finds most companies at Levels 1-2 of agentic AI maturity and identifies a capability-deployment verification gap as the core barrier to production use.
The survey organizes LLM-based multi-agent collaboration mechanisms into a framework with dimensions of actors, types, structures, strategies, and coordination protocols, reviews applications across domains, and identifies challenges for future research.
Code Broker deploys a five-agent hierarchy that combines LLM semantic analysis with static linting to generate actionable Python code quality reports.
citing papers explorer
-
Why Do Multi-Agent LLM Systems Fail?
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
-
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.
-
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
Terminus-4B, a Qwen3-4B post-trained with SFT and rubric-based GRPO, matches or beats frontier models as a terminal-execution subagent while cutting main-agent tokens ~30% on SWE-Bench-style tasks.
-
Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study
APIKG4Syn synthesizes API-oriented training data via knowledge graphs and Monte Carlo search to fine-tune a 7B model that reaches 25% pass@1 on HarmonyOS code generation, beating untuned GPT-4o at 17.59%.
-
Assistance to Autonomy: A Systematic Literature Review of Agentic AI across the Software Development Life Cycle
Systematic review of agentic AI in the SDLC finds output verifiability drives industrial adoption in later phases, with Planner-Executor-Reviewer as the dominant pattern, plus a new multi-agent LLM screening pipeline for high-volume SLRs.
-
Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt-Engineering Quality Assurance
A case study of iterative auditing on AEGIS LLM multi-agent specs found 51 defects over nine rounds with non-monotonic convergence, a post-hoc seven-category taxonomy, and replications showing category kappa of 0.80.
-
FormIDEAble: Safe and Socially-aware Autonomous Systems
FormIDEAble models human-agent cooperation as a Priced Timed Markov Decision Process and solves cost-bounded reachability to produce socially-aware strategies with safety guarantees, shown in an evacuation example.
-
Agentic AI in Industry: Adoption Level and Deployment Barriers
Qualitative interview study of 16 practitioners finds most companies at Levels 1-2 of agentic AI maturity and identifies a capability-deployment verification gap as the core barrier to production use.
-
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
The survey organizes LLM-based multi-agent collaboration mechanisms into a framework with dimensions of actors, types, structures, strategies, and coordination protocols, reviews applications across domains, and identifies challenges for future research.
-
Code Broker: A Multi-Agent System for Automated Code Quality Assessment
Code Broker deploys a five-agent hierarchy that combines LLM semantic analysis with static linting to generate actionable Python code quality reports.