Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems

arXiv:2610.08101 · cs.AI · Submitted 2026-10-06 · Read on arXiv

cs.AI

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: 39 pages, 7 figures, 30 tables (including appendix)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes

Sources

• AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation
• Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
• LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
• Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
• Multi-Agent Transactive Memory
• MemTX: Transactional Belief Commit for Stateful Agent Memory
• MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
• Dealing with observability in interaction-based Offline Runtime Verification of Distributed Systems
• Governed Shared Memory for Multi-Agent LLM Systems
• GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
• CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies
• StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems
• TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory
• PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
• Beyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise Workflows
• Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead
• AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
• AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems