{"total":22,"rows":[{"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":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2604.27865","title":"KellyBench: A Benchmark for Long-Horizon Sequential Decision Making","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2605.16358","title":"LEAF: A Living Benchmark for Event-Augmented Forecasting","created":"2026-05-09","cited_by_count":2,"area":null},{"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":"2604.26106","title":"Evaluating Strategic Reasoning in Forecasting Agents","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2607.14051","title":"Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.24573","title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","created":"2026-07-27","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":"2608.29696","title":"Ideation Arena: Evaluating LLM Generated Research Ideas with Battle-style Human Expert Assessment","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.01337","title":"LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2603.17212","title":"Adaptive Contracts for Cost-Effective AI Delegation","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.24996","title":"From Forecasting Leaderboards to Deployment Decisions: A Fail-Closed Certification Protocol","created":"2026-06-23","cited_by_count":0,"area":null},{"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":"2607.06166","title":"When do prophets profit in prediction markets?","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.06656","title":"Robust Human-AI Complementarity under Uncertainty","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.11653","title":"Bet on Features: Anytime-Valid and Feature-Aware Auditing of Conditional Quantile Forecasters","created":"2026-07-13","cited_by_count":0,"area":null},{"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":"2609.35879","title":"CruxBench: A Benchmark of Information Discovery","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}