{"total":59,"rows":[{"id":"2510.17638","title":"LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena","created":"2025-10-20","cited_by_count":40,"area":null},{"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":"2512.25070","title":"Scaling Open-Ended Reasoning to Predict the Future","created":"2025-12-31","cited_by_count":21,"area":"lr"},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"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":"2604.22748","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","created":"2026-04-24","cited_by_count":14,"area":"wm"},{"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":"2604.14199","title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","created":"2026-04-03","cited_by_count":12,"area":null},{"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":"2512.08868","title":"EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2601.13836","title":"FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs","created":"2026-01-20","cited_by_count":7,"area":"mllm"},{"id":"2512.05671","title":"ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education","created":"2025-12-05","cited_by_count":6,"area":null},{"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":"2603.20807","title":"BenchBench: Benchmarking Automated Benchmark Generation","created":"2026-03-21","cited_by_count":5,"area":null},{"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":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"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":"2604.27865","title":"KellyBench: A Benchmark for Long-Horizon Sequential Decision Making","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2605.22681","title":"Scientific reasoning does not reliably translate into scientific forecasting in frontier AI","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2608.12841","title":"AQuA: Recursively Self-Improving Quantitative Trading Research Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2511.18394","title":"Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Asking","created":"2025-11-23","cited_by_count":2,"area":null},{"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":"2605.27904","title":"Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting","created":"2026-05-27","cited_by_count":2,"area":null},{"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":"2606.29661","title":"Diversity is the Strength of the AI Crowd","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2601.06088","title":"PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.13545","title":"TruthTensor: Evaluating LLMs through Human Imitation on Prediction Market under Drift and Holistic Reasoning","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2603.03322","title":"Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.02378","title":"YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.23072","title":"Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis","created":"2026-04-24","cited_by_count":1,"area":"lr"},{"id":"2607.14051","title":"Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.04009","title":"SocietyBench: Forecasting Counterfactual Social-World Evolution","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.20920","title":"ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction","created":"2026-08-21","cited_by_count":1,"area":null},{"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":"2606.02433","title":"ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2607.01661","title":"Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.03015","title":"Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.04389","title":"Decentralized Aggregation of LLM Predictions via Wagering Mechanisms","created":"2026-07-05","cited_by_count":0,"area":null},{"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":"2607.25554","title":"Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis","created":"2026-07-28","cited_by_count":0,"area":"lr"},{"id":"2607.29503","title":"The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.24001","title":"Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Prediction","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"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":"2609.22246","title":"The Corroboration Illusion: When More News Makes LLM Forecasts Less True","created":"2026-09-05","cited_by_count":0,"area":null},{"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":"2609.33257","title":"Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts","created":"2026-09-27","cited_by_count":0,"area":null},{"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":"2609.35879","title":"CruxBench: A Benchmark of Information Discovery","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36689","title":"CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"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"},{"id":"2610.14073","title":"Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}