# MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems

arXiv: https://arxiv.org/abs/2602.19843 · HTML: https://mlsanity.com/paper/2602.19843/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 62 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 23 of 23)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents](https://mlsanity.com/paper/2408.00989/) (2024)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation](https://mlsanity.com/paper/2402.11443/) (2024)
- [Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2502.14321/) (2025)
- [Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.23352/) (2025)
- [ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents](https://mlsanity.com/paper/2407.00132/) (2024)
- [Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning](https://mlsanity.com/paper/2502.11799/) (2025)

## Built on by (most cited first, 16 of 16)

- [MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals](https://mlsanity.com/paper/2605.07509/) (2026)
- [VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems](https://mlsanity.com/paper/2605.17467/) (2026)
- [CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring](https://mlsanity.com/paper/2605.19240/) (2026)
- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)
- [OctoNest: Adaptive Cross-Device Execution through Stateful Control](https://mlsanity.com/paper/2606.20487/) (2026)
- [Instruction Bleed: Cross-Module Interference in Prompt-Composed Agentic Systems](https://mlsanity.com/paper/2606.26356/) (2026)
- [Emergence of Agentic AI: A Review on Evolution, Background, Working Principles, Applications, Adoption Factors, and Future Research Directions](https://mlsanity.com/paper/2608.18110/) (2026)
- [ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures](https://mlsanity.com/paper/2609.16986/) (2026)
- [A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems](https://mlsanity.com/paper/2609.19524/) (2026)
- [Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault](https://mlsanity.com/paper/2609.32802/) (2026)
- [The Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces](https://mlsanity.com/paper/2609.32825/) (2026)
- [Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation](https://mlsanity.com/paper/2610.00349/) (2026)
- [Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents](https://mlsanity.com/paper/2610.04375/) (2026)
- [Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues](https://mlsanity.com/paper/2610.16117/) (2026)
- [AuthGateBench: Benchmarking LLMs as Authorization Gate](https://mlsanity.com/paper/2610.16426/) (2026)
- [BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems](https://mlsanity.com/paper/2610.17805/) (2026)

## Abstract (arXiv)

As LLM-based Multi-Agent Systems (MAS) are increasingly deployed for complex tasks, ensuring their reliability has become a pressing challenge. Since MAS coordinate through unstructured natural language rather than rigid protocols, they are prone to semantic failures (e.g., hallucinations, misinterpreted instructions, and reasoning drift) that propagate silently without raising runtime exceptions. Prevailing evaluation approaches, which measure only end-to-end task success, offer limited insight into how these failures arise or how effectively agents recover from them. To bridge this gap, we propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of MAS. We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures, and inject them via three non-invasive mechanisms: prompt modification, response rewriting, and message routing manipulation. Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors that we organize into four tiers: mechanism, rule, prompt, and reasoning. This tiered view enables fine-grained diagnosis of where and why systems succeed or fail. Our findings reveal that stronger foundation models do not uniformly improve robustness. We further show that architectural topology plays an equally decisive role, with iterative, closed-loop designs neutralizing over 40% of faults that cause catastrophic collapse in linear workflows. MAS-FIRE provides the process-level observability and actionable guidance needed to systematically improve multi-agent systems.