Hugging Face Blog

Back to The Future: Evaluating AI Agents on Predicting Future Events

arXiv AI
Sep 25

Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents

Forecast-Dojo is a replayable environment designed to benchmark and train large language model (LLM) forecasting agents. It integrates resolved prediction‑market questions with dated news, enabling agents to research events and revisit predictions at successive historical dates. The platform includes 1,568 Polymarket events, 18.8 million dated news articles, and supports repeated evaluation, training interactions, and outcome feedback, with evidence that research tools lower Brier scores across 12 tested models, though all models still lag behind historical market forecasts.

By Liqin Ye, Haorui Wang, Fardin Ahmed, Rongzhi Zhang, Yuan He, Ziyuan Lin, Yanbin Yin, Jing Peng, Michael Galarnyk, Sudheer Chava, Chao Zhang
arXiv Machine Learning
Nov 2

Benchmarking Forecasting Agents on Yesterday's Tomorrows

The paper introduces FABench, a scalable backtesting environment designed to evaluate forecasting agents. FABench automatically discovers events, generates questions, and resolves outcomes for any past forecast date, allowing continuous renewal beyond model training cutoffs. In initial tests, retrieval improves Brier scores across eight models, with top agents matching or surpassing market consensus on 54 Polymarket-linked questions, yet analysis shows persistent evidence‑weighting failures that highlight room for improvement.

By Yuxuan Wang, Yishu Wang, Jiaqi Deng
arXiv Computation and Language
Nov 4

Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making

The paper introduces Agent-Authored World Modeling (AAWM), a training method that replaces traditional next-observation prediction with decision-oriented supervision. AAWM constructs training targets by having the agent identify what it needs to know before acting, then retrieves relevant transition evidence across trajectories to synthesize these needs into learning signals. Experiments across multiple environments demonstrate that this decision-aware approach yields more effective learning than conventional next-observation prediction.

By Guangfeng Cai, Kaibing Yang, Shuo He, Yu Li, Shengtian Yang, Jiaqi Lv, Lei Feng
arXiv AI
Oct 15

GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation

GIFT‑Eval‑CTX is a new benchmark for contextual forecasting that tests whether models can use verified future information to produce accurate time‑series predictions. It builds on GIFT‑Eval and contains 10,000 instances across 20 datasets, each annotated with macro‑level and micro‑level effects derived from actual future events. The benchmark evaluates traditional TSFMs, advanced LLMs, and agentic systems, showing that structured effects can substantially lower MASE for models like GPT‑5.6 Sol and Claude Opus 4.8, with MoiraiAgent achieving the best overall performance.

By Xu Liu, Hanshu Yan, Taha Aksu, Quang Pham, Zhongzheng Qiao, Jun Hao Liew, Silvio Savarese, Doyen Sahoo, Junnan Li
arXiv AI
Sep 12

Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks

The article "Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks" surveys the lack of a standard definition for AI agents and organizes this ambiguity into five dimensions: environmental interaction, learning and adaptation, autonomy, goal‑directed behavior, and temporal coherence. It reviews how each dimension has been conceptualized in prior work and compiles the metrics, benchmarks, and evaluation frameworks used to assess them. The authors also introduce the Agent Compendium, a public digital resource that extends these evaluation methods, aiming to provide a common structure for evaluating and comparing agent capabilities across AI systems.

By Mia Lassiter, Brinnae Bent