Latest Research in Multi-Agent Systems and Negotiation

Top Research Topics in Multi-Agent Systems and Negotiation

• Artificial Intelligence — 45 papers
• Scientific Computing and Data Management — 18 papers
• Multi-Agent Systems and Negotiation — 15 papers
• Explainable Artificial Intelligence (XAI) — 13 papers
• Software Engineering — 12 papers
• Adversarial Robustness in Machine Learning — 11 papers
• Computation and Language — 10 papers
• Ethics and Social Impacts of AI — 7 papers
• Access Control and Trust — 6 papers
• Human-Computer Interaction — 6 papers

Highest-Cited Papers

1. A Failure-Preserving Replay of Integrity Predicates in a Minimal Persistent Agent Store
2. Recognition Without Qualification Authority: A Technical Note
3. Evidentiary Boundaries in Runtime Interpretation: A Technical Note
4. Evidentiary Boundaries in Runtime Interpretation: A Technical Note
5. Governed Semantic Triangulation: A Protocol Primitive for Bounded AI Claims
6. TRACE: Evaluating a Control Set Across Agent Architectures
7. Verification Bandwidth Under Correlated Evaluators: What an Effective-Sample-Size Statistic Measures in an Acceptance Cascade
8. Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding
9. Verification Bandwidth Under Correlated Evaluators: What an Effective-Sample-Size Statistic Measures in an Acceptance Cascade
10. Weft: Evidence-Gated Version Control for Autonomous Agent Swarms
11. When a Replay Benchmark Fails Before Replay: Prospectively Locked, Fail-Closed Calibration for Tool-Agent Evaluation
12. ReceiptOS: Recomputable Evidence and Counterfactual Verifier Conformance
13. ReceiptOS: Recomputable Evidence and Counterfactual Verifier Conformance
14. Auditable AI-Assisted Research Writing: An Engineering Discipline with Pre-Registered Process Observation
15. The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior
16. Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations
17. Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog
18. CAA-X V5: CAA-R – Robotic Extension
19. Who checks the answer key? Ground-truth defects in eight professional-practice benchmarks
20. EHOX Universal Pitch Deck v3 — Silicon-Level AI Governance for Defence, Aerospace, Medical, Mobility