{"total":23,"rows":[{"id":"2606.01770","title":"Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams","created":"2026-06-01","cited_by_count":27,"area":"agents"},{"id":"2602.22808","title":"MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks","created":"2026-02-26","cited_by_count":15,"area":"agents"},{"id":"2603.07980","title":"\\$OneMillion-Bench: How Far are Language Agents from Human Experts?","created":"2026-03-09","cited_by_count":13,"area":"agents"},{"id":"2604.18576","title":"Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs","created":"2026-04-20","cited_by_count":10,"area":"agents"},{"id":"2601.12259","title":"FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains","created":"2026-01-18","cited_by_count":9,"area":"agents"},{"id":"2510.16720","title":"Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"id":"2512.00417","title":"CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency","created":"2025-11-29","cited_by_count":5,"area":"agents"},{"id":"2601.05039","title":"FinDeepForecast: A Live Multi-Agent System for Benchmarking Deep Research Agents in Financial Forecasting","created":"2026-01-08","cited_by_count":4,"area":"agents"},{"id":"2602.14257","title":"AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents","created":"2026-02-15","cited_by_count":3,"area":"agents"},{"id":"2608.12841","title":"AQuA: Recursively Self-Improving Quantitative Trading Research Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2602.06486","title":"JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks","created":"2026-02-06","cited_by_count":2,"area":"agents"},{"id":"2606.00644","title":"ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment","created":"2026-05-30","cited_by_count":2,"area":"agents"},{"id":"2606.21013","title":"Agentic Time Machine as an Infrastructure for Future-Event Forecasting","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2608.23058","title":"LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2609.01294","title":"Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2604.26235","title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","created":"2026-04-29","cited_by_count":0,"area":"agents"},{"id":"2605.30858","title":"ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2607.13602","title":"Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2609.05905","title":"From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.28876","title":"Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.33470","title":"LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.00710","title":"ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.03591","title":"HazardWeaver: Scientific Route Selection for Hazard Analysis Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}