mlsanityData to 14 Oct 2026

MTTR-A: Measuring Cognitive Recovery Latency in Multi-Agent Systems

arXiv 2511.20663 ↗First posted 8 Nov 2025cs.MA cs.AI cs.SYcited by 2

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Reliability in multi-agent systems (MAS) built on large language models is increasingly limited by cognitive failures rather than infrastructure faults. Existing observability tools describe failures but do not quantify how quickly distributed reasoning recovers once coherence is lost. We introduce MTTR-A (Mean Time-to-Recovery for Agentic Systems), a runtime reliability metric that measures cognitive recovery latency in MAS. MTTR-A adapts classical dependability theory to agentic orchestration, capturing the time required to detect reasoning drift and restore coherent operation. We further define complementary metrics, including MTBF and a normalized recovery ratio (NRR), and establish theoretical bounds linking recovery latency to long-run cognitive uptime. Using a LangGraph-based benchmark with simulated drift and reflex recovery, we empirically demonstrate measurable recovery behavior across multiple reflex strategies. This work establishes a quantitative foundation for runtime cognitive dependability in distributed agentic systems.

Key facts. Cited by 2 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 20 of its 38 references that are in the map. First posted on arXiv 8 Nov 2025.

Builds on

20 of 38 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution26 Mar
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug

Other references · 18

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  9. 2016Concrete Problems in AI Safetycited by 1,642
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  11. 2024DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learningcited by 214
  12. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 206
6 more
  1. 2024On the Effects of Data Scale on UI Control Agentscited by 194
  2. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 137
  3. 2024LLM Multi-Agent Systems: Challenges and Open Problemscited by 120
  4. 2024Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?cited by 56
  5. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  6. 2022TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoringcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Kalman-Inspired Runtime Stability and Recovery in Hybrid Reasoning Systemscited by 1
  2. 2026Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems
  2. 2026Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents
  3. 2026Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactions
  4. 2026Sentry: Learning to Recover from LLM Agent Failures at Test Time
  5. 2026A Self-Healing Framework for Reliable LLM-Based Autonomous Agents
  6. 2026Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems
  7. 2026Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems
  8. 2026Silent Failure in LLM Agent Systems: The Entropy Principle and the Inevitable Disorder of Autonomous Agents