When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary

arXiv:2609.15397 · cs.AI, cs.DB, cs.DC, cs.SE · Submitted 2026-09-14 · Read on arXiv

cs.AI, cs.DB, cs.DC, cs.SE

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 11 pages, 4 tables. Artifact: https://github.com/flame-stream/mcp-annotation-census

Code: https://github.com/flame-stream/mcp-annotation-census

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

Terminology

• AI Agents — 4× in this paper · explained in 2 episodes
• Actor — 3× in this paper · explained in 3 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Model Context Protocol — 3× in this paper
• Agentic System — 1× in this paper · explained in 2 episodes
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
• Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
• Cordon: Semantic Transactions for Tool-Using LLM Agents
• CoAgent: Concurrency Control for Multi-Agent Systems
• Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces
• S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination
• Revisable by Design: A Theory of Streaming LLM Agent Execution
• Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
• A Large-Scale Dataset of MCP Implementations on GitHub

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection