Latest Research in Artificial Intelligence
124 research papers · 2026 median publication year
Top Research Topics in Artificial Intelligence
- Artificial Intelligence — 29 papers
- Adversarial Robustness in Machine Learning — 7 papers
- Explainable Artificial Intelligence (XAI) — 7 papers
- Ethics and Social Impacts of AI — 5 papers
- Scientific Computing and Data Management — 4 papers
- Computation and Language — 4 papers
- Software Engineering — 4 papers
- Software System Performance and Reliability — 3 papers
- Cryptography and Security — 3 papers
- Topic Modeling — 3 papers
Highest-Cited Papers
- Demoting the Master Control Program: Deterministic Orchestration of a Fleet of LLM Agents
- SYNTAX: A Human-AI Collaboration Protocol for Durable Agent Work
- SYNTAX: A Human-AI Collaboration Protocol for Durable Agent Work
- Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents
- Teaching a Large Language Model Tutor to Withhold the Answer: A Supervisor Architecture and an Evidence-Driven Method for Tuning Socratic Behavior
- Agent Safety Should Be a Runtime Contract
- TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents
- AI Guardrail Survival under Single-Cycle Agentic Self-Summarization
- Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy
- A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline
- Joint Lyapunov Certificates for K-Agent Generative AI Governance: Stochastic Stability, Emergent Ensemble Risk, and Zero-Knowledge Governance Attestation
- Finite Regenerative Containment for Adversarial AI Evaluation
- Deterministic External State Dynamics for Reproducible Long-Horizon LLM Agents
- SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents
- Homebot: A Personal AI Agent for Conversational Home Assistance and Automation
- Standardized Observability Taxonomies for Multi‑Agent AI Systems in Decentralized Networks
- TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views
- Stability Before Behavior: A Lean 4 Certified Control Layer for Language-Model Agents
- Governed Imagination: Admitting Learned Rollouts as Evidence in a Lineage-Bounded Robot Authorization Runtime
- Standardized Observability Taxonomies for Multi‑Agent AI Systems in Decentralized Networks