Forecasting as a New Frontier
of Intelligence

Topics of Interest

The main topics of our workshop include, but are not limited to, the following aspects:

• Architectures: agentic systems, LLM-as-a-Prophet, foundation models and world models.
• Evaluation: automated event generation, metrics and benchmark design.
• Reasoning: probabilistic reasoning, calibration, causal and temporal inference.
• Retrieval: search architecture, credibility assessment and retrieval-augmented generation.
• Foundations: scoring rules, online learning, and decision-theoretic frameworks.
• Markets & Society: prediction markets, societal impacts of AI-driven forecasting.

Oral Presentations (5)

• Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs Kevin Murphy
• Allocation, Not Volume: Test-Time Compute for Agentic Forecasting Atin Aboutorabi, Gaetan de Rassenfosse, Nicolas Flammarion, Maksym Andriushchenko
• Forecasting Emerges from Auto-Regressive Pretraining: Latent Predictive Structure in Language Models Alexis Roger, Prateek Humane, Zhenghan Tai, Gwen Legate, Andrei Mircea, Vasilii Feofanov, Irina Rish
• Forecasting Motion in the Wild Neerja Thakkar, Shiry Ginosar, Jacob C Walker, Jitendra Malik, Joao Carreira, Carl Doersch
• FutureSim: Replaying World Events to Evaluate Adaptive Agents Shashwat Goel, Nikhil Chandak, Arvindh Arun, Ameya Prabhu, Steffen Staab, Moritz Hardt, Maksym Andriushchenko, Jonas Geiping

Spotlights (10)

• Approximate Recall, Approximate Forecasts: Recall as a Diagnostic for LLM Forecasting Errors Shubhaankar Gupta, Prashanth Bhaskara, Seojoon Yeon
• Beyond Accuracy: Can LLM Forecasters Profit on Prediction Markets? Steven Henry, Jillian Ross, Alana Marzoev, Eric So, Andrew Lo
• Curating the Future: A Scalable Recipe for Training Open-Ended Forecasters Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping
• Decentralized Aggregation of LLM Predictions via Wagering Mechanisms Yuhong Luo, David Pennock, Xintong Wang
• Forecast-to-Trade: Hierarchical Reinforcement Learning for Decision-Aware Financial Forecasting Zijie Zhao, Roy E. Welsch
• ForecastBench-Sim: A Simulated-World Forecasting Benchmark Jaeho Lee, Nick Merrill, Ezra Karger
• ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory Yurui Chang, Yongkang Du, Yuanpu Cao, Jinghui Chen, Lu Lin
• Future-as-Label: Scalable Supervision from Real-World Outcomes Paul Wilczewski, Benjamin Turtel, Kris Skotheim
• Reaching the frontier of AI forecasting with reinforcement learning Scott Jeen, Matthew Aitchison, Max Clark, Toby Shevlane, Ben Day
• When do prophets profit in prediction markets? Anri Gu, Nicole Kagan, Alec Sun, Jibang Wu, Haifeng Xu

Posters (69)

• A Black-Box Reduction from Regret to Multi-Level Coverage Tuo Liu, Edgar Dobriban, Francesco Orabona
• A Lightweight Deep Learning Approach to Spatiotemporal Heat Forecasting Euan Marney, Linus Ericsson
• Accurate Forecasts Do Not Ensure Safe Decision Jaehyun Pyun, Seunghun Moon, Suk-Ju Kang
• AgentRx: A Benchmark for Multimodal Clinical Forecasting with LLM Agents Baraa Al Jorf, Farah E. Shamout
• Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting Hui Dai, Ryan Teehan, Parsa Torabian, Mengye Ren
• Alive and Predicting: A Live Evaluation of Multi-Step Forecasting Agents Will Wu, Hui Dai, Mengye Ren
• An adversarial tournament design for efficiently probing the frontier of AI forecasting Ben Day, Scott Jeen, Simion-Vlad Bogolin, Max Clark, Toby Shevlane
• Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis Yongqiang Chen, Guangyi Chen, Yuewen Sun, Kun Zhang
• Arbitrage-Free Forecasts from Language Models via Coherence Projection Anany Kotawala
• Auditing Actionability in AI Forecasting Interfaces Srinivas Raghav V C, Aditya Sri Ram Barnala
• Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents Issue Yishu Wang, Yuxuan Wang, Hanyang Tang
• Decision-Relevant Predictions with Joint Scoring Rules Rubi Hudson
• DELPHYNE: A Pre-Trained Model for General and Financial Time Series Xueying Ding, Aakriti Mittal, Achintya Gopal
• Discover then Refine: A Joint Multiple Choice Learning and Flow Matching Framework for Heat Demand Forecasting Malek Mahjoub, Vasile-Marian Scuturici
• Diversity is the strength of the AI crowd Matthew Aitchison, Scott Jeen, Toby Shevlane, Ben Day
• Do Language Models Update their Forecasts with New Information? Moy Yuan, Zifeng Ding, Andreas Vlachos
• Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting Yingshuo Wang, Xian Sun, Zexin Zhuang, Yanhang Li, Zhichao Fan
• DuoMamba: A Decomposition-Free State Space Model for Long-Term Time Series Forecasting Anna-Alina Bondarets, Taras Rumezhak, Volodymyr Karpiv
• Efficient Forecasting of Task Failures in LLM Agents through Adaptive Fault Injection Vartika Sengar, Parth Thakkar, Pranoy Panda, Shrey Satapara, Emmy Liu, Vijay Viswanathan, Sho Takemori, Graham Neubig, Chaitanya Devaguptapu
• Elicitation Format Drives Divergent LLM Geopolitical Forecasts Suhas Hariharan, George Ghetiu, Ari Weiler-Ofek, Hao Jie Pe, Tatsan Kantasit, Michal Bravansky, Raphael Tang
• Enabling Uncertainty-Aware Time-Series Forecasting in Federated Learning for Urban Water Dynamics Golnoosh Abdollahinejad, Patrik Okanovic, Denisa-Andreea Constantinescu, Sergey Shevchik, Torsten Hoefler, David Atienza
• Evaluating Long-Form Forecasts by Their Effect on Downstream Predictions Jeremy Qin, Nikhil Chandak, Shashwat Goel, Hardik Bhatnagar, Ameya Prabhu, Jonas Geiping, Moritz Hardt, Maksym Andriushchenko
• Forecasting Model Success at Inference Time: Calibrated Probabilistic Forecasts for Cost-Optimal LLM Cascades Varun Kotte
• Forecasting Time-Varying Correlation Matrices with Large Language Models Georgii Petrov, Ilya Novitskiy, Mironov Kirill Sergeevich, Sergey Muravyov, Valeria Efimova, Viacheslav Shalamov
• Forecasting With LLMs: Improved Generalization Through Feature Steering Humzah Merchant, Bradford Levy
• Forecasts as a Behavioral Probe of Language Models Simon Mahns, Elliot James Paschal, Nicole Kagan
• Foresight-Phys: A Benchmark for Forecasting the Results of Physical Experiments Nikita Kazeev, Ian Babich
• ForesightFlow: An Information Leakage Score Framework for Prediction Markets Maksym Nechepurenko
• Forward-Chaining Temporal Point Process Chao Yang, Wendi Ren, Shuang Li
• From Events to Impacts: Calibrated Decomposition for LLM-Based Geopolitical Forecasting Bernhard Escherich, Christian Schroll, Dr. La Toya Waha
• From Marks to Narratives: Language-Augmented Spatio-Temporal Point Processes Zheng Dong, Xiaoyue Liu
• From Narrative to Auditable Forecasts: An Agentic Scaffold for Probabilistic Forecasting Yuanpu Cao, Yongkang Du, Yurui Chang, Lu Lin, Jinghui Chen
• Generative Bayesian Computation for Probabilistic Forecasting with Discrete Events Nicholas Polson, Vadim Sokolov
• GENERATIVE TRAFFIC FORECASTING: PRESERVING SHOCKWAVE TOPOLOGY WITH DIFFUSION MODELS Md. Iqramul Hoque, Md Ibrahim Khalil, Tasfia Noor Chowdhury, Tanjim Binta Hasan Jerin
• HMTMO-GP: Hierarchical Multi-Task Multi-Output Gaussian Processes Yan Chen, Ti-chiun Chang, Kevin Stone
• How Predictable is AI Progress? David Mayo, Abdulrahman Alabdulkareem, Albert Eaton Shaw, Colin Conwell, Andrey Gizdov, Andrei Barbu, Boris Katz, Brian Cheung
• Iterative Computation as Anytime Forecasting: Dense Supervision for Calibrated Trajectories in Recurrent World Models Bao N Nguyen Truong, Hoyeon Chang, Alexander Rubinstein, Seong Joon Oh
• Latent Market Dynamics: A World Model Framework for Agentic Prediction Markets Jay Oza, Hrishikesh Yadav
• Latent Stochastic Interpolants for Probabilistic Time Series Forecasting Max Bourgeat, Sobihan Surendran
• Leakage-Aware Benchmarking of LLM Forecasting: Real-Time Nowcasts as the Decision-Time Input for Macro Factor Ranking Mao Guan, Qian Chen
• MacroBench: Measuring Frontier LLM Macroeconomic Forecasting Ability Arjun Neervannan, Sujai Hiremath, Sumiran Singh Thakur, Guanghan Ning, Deniz Zorlu
• Measuring Source-Induced Bias in LLM Forecasts with Prediction Markets Mykola Khandoga, Yevhen Kostiuk, Anton Polishko, Kostiantyn Kozlov, Yurii Filipchuk, Dmytro Zamriy, Artur Kiulian
• Mix, Don’t Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining Aaryan Nagpal, Debdeep Sanyal, Dhruv Kumar, Murari Mandal, Saurabh Deshpande
• One Token per Trade: Multi-Resolution Limit Order Book Forecasting with a Foundation Model Srijan Sood, Maxime Kawawa-Beaudan, Zhijin Guo, Daniel Borrajo
• OptimismBench: Measuring Forecasting Bias in Language Model Judgment Seonglae Cho, Adriano Koshiyama
• Outcome-Free Audits and Repairs for LLM Forecasters Juliana Li, Diya Sreedhar
• Period-Aware Inductive Bias Versus Scale on Influenza-like Illness Forecasting YongKyung Oh, Alex Bui
• Physics-Informed Bidirectional Graph Networks for Traffic Prediction: Deriving Message Passing Direction from Traffic Flow Theory Benjamin Lartey
• Polynomial Input Preconditioning for Zero-Shot Time Series Forecasting Jerry Han, Alex Kawaja, Benjamin Cole, Elad Hazan
• Preference Optimization Drives Monoculture in LLM Prediction Markets James Begin, Brendan Gho, Suman Muppavarapu, Tyson Tsay, Atharva Mohan, Afnan Shaik, Ruizhe Li, Vasu Sharma, Archana Vaidheeswaran, Kevin Zhu
• Presentation Robustness for LLM Forecasters Leon Luo
• Proxy Scoring Enables Benchmarking LLM Forecasters Without Waiting for Outcomes Julius Hege, Gitta Kutyniok
• Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score Mariya Pavlova, Harrison Bo Hua Zhu, Elizaveta Semenova, Yingzhen Li
• Reflexivity as Prompt: Does Awareness of Self-Reinforcing Market Dynamics Improve LLMs as Financial Market Forecasters? Eugene W Park
• Repackaging Temporal Evidence: A Unifying Interface for Temporal Prediction Hao-Run Cai, Hao-Chen Liu, Ji-Yang Zhao, Yu-Jie Lai, Han-Jia Ye
• RIFT: Reliability of LLM and Physics Forecasters across Time-Horizons in Coupled PDE Systems Kuntal Thakur, Ayan Banerjee, Christian Stoddard, Majid M Sadeghi, Sandeep Gupta
• Robustness of Multimodal Foundation-Model Forecasting for Postoperative Cancer Outcomes KuanTing Wu
• SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction Yanan He, Yunshi Wen, Xin Wang, Tengfei Ma
• SciPaths: Forecasting Pathways to Scientific Discovery Eric Chamoun, Yizhou Chi, Yulong Chen, RUI CAO, Zifeng Ding, Michalis Korakakis, Andreas Vlachos
• Semantics-Enhanced Retrieval-Augmented Time Series Forecasting Shiqiao Zhou, Zipeng Wu, Holger Schöner, Edouard Fouché, IAG Wilson, Shuo Wang
• Simulation-Augmented Multi-Step Split Conformal Prediction for Aggregated Forecasts Andro Sabashvili
• StretchTime: Adaptive Time Series Forecasting via Symplectic Attention Yubin Kim, Viresh Pati, Jevon Twitty, Vinh Pham, Shihao Yang, Jiecheng Lu
• Temporally Supervised Linear Probes Improve LLM Forecasts Marius Binner
• TimeRouter: Efficient and Adaptive Routing of Time Series Foundation Models Kanghui Ning, Yushan Jiang, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka, Dongjin Song
• VSTF: Vision and Sequence Models for Time-Frequency Time Series Forecasting Junlin Liu, Yanting Yang, Ren Wang
• What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions Shuqi Gu, Yongxiang Zhao, Baoyu Jing, Kan Ren
• What Should We Forecast? Benchmarking Agents on Early Question Discovery Keisuke Ueda, Veniamin Veselovsky, Robert West
• When Does Evidence Help Prompted LLM Forecasting? Evidence Access and Prompt Structure Across 12 Models Akram Naoufel Tabet, mitja luštrek
• WorldFork: Auditable Branching Rollouts for LLM Forecasting Hanson Wen, Shing Cheung James Gui

Key Dates

Submission Guidelines

Forecasting Agent Hackathon