Latest Research in Artificial Intelligence

Top Research Topics in Artificial Intelligence

• Artificial Intelligence — 59 papers
• Scientific Computing and Data Management — 24 papers
• Ethics and Social Impacts of AI — 24 papers
• Computation and Language — 18 papers
• Cellular Automata and Applications — 17 papers
• Adversarial Robustness in Machine Learning — 15 papers
• Software Engineering — 14 papers
• Explainable Artificial Intelligence (XAI) — 11 papers
• Machine Learning — 11 papers
• Multi-Agent Systems and Negotiation — 8 papers

Highest-Cited Papers

1. The collective turing test: large language models can generate realistic multi-user discussions (1 citations)
2. When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops
3. Repair as Representational Work: Integration Bottlenecks in AI-Assisted Development
4. A Graph-Native Bitemporal Memory Store for Conversational AI Agents
5. CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games
6. Do Models Fake Alignment Without Clear Consequences?
7. Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests
8. Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data
9. Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control
10. What Licenses Sameness Through Change? A Short Orientation to the Identity-Persistence Program Toward a Structural Theory of Regime Specification
11. ANT 3.0: Angular-Norm Transport, Verified Whole-Object Digestion, and Living Colony Computation [CPU-First]
12. Grading the Narrators: An Isnād–Rijāl Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems
13. Context Observability: A Data-Observability Framework for Governing Shared Memory in Multi-Agent AI Coding Systems
14. Provenance-Tiered Conflict Resolution in Agent Memory
15. ANT (Angular-Norm Transport) & Agentized Neural Computation: A Living Colony for Turning Data, Graphs, Models, and Meaning Trajectories into Verified Executable Knowledge | [CPU-First [!]]
16. The Evaluator Trust Boundary: A defect class in AI evaluation infrastructure, its prevalence across 36 organizations, and its removal by training
17. Context Observability: A Data-Observability Framework for Governing Shared Memory in Multi-Agent AI Coding Systems
18. ANT: Angular-Norm Transport and Agentized Neural Computation [CPU-First]
19. The Evaluator Trust Boundary: A defect class in AI evaluation infrastructure, its prevalence across 36 organizations, and its removal by training
20. ANT (Angular-Norm Transport) & Agentized Neural Computation: A Living Colony for Turning Data, Graphs, Models, and Meaning Trajectories into Verified Executable Knowledge | [CPU-First [!]]