{"total":16,"rows":[{"id":"2503.16858","title":"MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering","created":"2025-03-21","cited_by_count":55,"area":"lr"},{"id":"2510.01499","title":"Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2512.25070","title":"Scaling Open-Ended Reasoning to Predict the Future","created":"2025-12-31","cited_by_count":21,"area":"lr"},{"id":"2502.05253","title":"LLMs Can Teach Themselves to Better Predict the Future","created":"2025-02-07","cited_by_count":14,"area":"lr"},{"id":"2510.15096","title":"OpenEstimate: Evaluating LLMs on Reasoning Under Uncertainty with Real-World Data","created":"2025-10-16","cited_by_count":5,"area":"lr"},{"id":"2607.08046","title":"What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"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":"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":"2605.18843","title":"TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2609.17496","title":"Verifiable Social Reasoning for LLM Assistants","created":"2026-09-15","cited_by_count":1,"area":"lr"},{"id":"2605.30391","title":"Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate","created":"2026-05-28","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":"2607.25554","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":"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":"2609.28475","title":"When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2610.04109","title":"SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}