Latest Research in Computation and Language

Top Research Topics in Computation and Language

• Artificial Intelligence — 47 papers
• Scientific Computing and Data Management — 20 papers
• Computation and Language — 20 papers
• Machine Learning — 14 papers
• Explainable Artificial Intelligence (XAI) — 13 papers
• Multi-Agent Systems and Negotiation — 12 papers
• Ethics and Social Impacts of AI — 12 papers
• Software Engineering — 11 papers
• Adversarial Robustness in Machine Learning — 11 papers
• Human-Computer Interaction — 10 papers

Highest-Cited Papers

1. Execution-Time Authorization for AI Agents: A Formal Framework for Deterministic Governance Boundaries (22 citations)
2. Mirror Observerhood Lab II: Channel-Decomposed Reliability and the Limits of Reliability Tracking Alone (25 citations)
3. Versioned Meaning: How to Make Ontologies Audit-Stable (9 citations)
4. AIME2: toward a unified algebraic theory of explainability via approximate inverse operators (1 citations)
5. Provenance, Timestamp Evidence, and Source-Chain Auditability
6. Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
7. Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
8. Evidence-Ledger Adjudication for Claim-Evidence Traceability
9. A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
10. Will Scaling Improve Social Simulation with LLMs?
11. ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
12. HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following
13. TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models
14. SYSTEM EVOLUTION PROPOSALS (rlab #17) — E8 Intelligence Research
15. MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents
16. AgentGUI: An Interface for Observing and Steering Long-Running AI Agents
17. When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses
18. FirstResearch: Auditable Question Formation for LLM Scientific Discovery Agents
19. Verified Agentic AI (VAAI): A Multi-Agent Framework for Trustworthy Large Language Models
20. Geometry vs Binary: AI/Binary Failures — neural network fails at geometric reasoning spatia — E8 Intelligence Research