{"total":22,"rows":[{"id":"2506.21558","title":"Bench to the Future: A Pastcasting Benchmark for Forecasting Agents","created":"2025-06-11","cited_by_count":21,"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":"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":"2512.02436","title":"Agentic AI for Clustering, Relationship Discovery, and Semantic Trading in Prediction Markets","created":"2025-12-02","cited_by_count":2,"area":"agents"},{"id":"2604.26733","title":"FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards","created":"2026-04-29","cited_by_count":2,"area":"agents"},{"id":"2605.03310","title":"Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems","created":"2026-05-05","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":"2606.11816","title":"WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning","created":"2026-06-10","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":"2607.18084","title":"WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2604.04220","title":"TimeSeek: Temporal Reliability of Agentic Forecasters","created":"2026-04-05","cited_by_count":1,"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":"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":"2608.14270","title":"TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments","created":"2026-08-14","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":"2609.10092","title":"RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases","created":"2026-09-09","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":"2609.31563","title":"Multi-agent Scaling Across Disjunctive and Compensatory Tasks","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.36739","title":"Frontier Autolab: Organizational Memory, Adversarial Dissent and Temporal Leakage in Multi-Agent LLM Firms Across Fifty Years of Technological Change","created":"2026-09-29","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":"2610.19589","title":"JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}