{"total":20,"rows":[{"id":"2507.22358","title":"Magentic-UI: Towards Human-in-the-loop Agentic Systems","created":"2025-07-30","cited_by_count":43,"area":"agents"},{"id":"2604.07036","title":"ReDAct: Uncertainty-Aware Deferral for LLM Agents","created":"2026-04-08","cited_by_count":7,"area":"agents"},{"id":"2607.12338","title":"How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks","created":"2026-07-14","cited_by_count":4,"area":"agents"},{"id":"2602.14606","title":"Towards Selection as Power: Bounding Decision Authority in Autonomous Agents","created":"2026-02-16","cited_by_count":2,"area":"agents"},{"id":"2606.11625","title":"TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation Models","created":"2026-06-10","cited_by_count":2,"area":"agents"},{"id":"2606.21399","title":"Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2605.30802","title":"Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market Resolution","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2606.31023","title":"Certified Speculative Execution for Untrusted AI Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2608.02444","title":"ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.07583","title":"RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.24087","title":"Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2609.26086","title":"CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrieval","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2605.06522","title":"Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.27999","title":"Learning to Assign Prediction Tasks to Agents with Capacity Constraints","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2607.27984","title":"Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2607.28317","title":"One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2609.00275","title":"The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.07984","title":"From Event Logs to Governed Action: A BlueSky Agenda for Agentic Process Mining","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.12039","title":"Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2610.09115","title":"From Uncertainty to Action: Learning to Steer LLM Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}