Research map / Large language models / Agents, code and math
FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen, Tianci He, Yali Liao, Yixiao Tian, wangjinpeng.levi, Zaiyuan Wang, YangYang, Lingyue Yin, Mingren Yin, Zhu Zhenwei and 20 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| downsample yes/no prediction-market events (ablation) | FutureX event set · one week of prediction-market events | number of events: 193 -> 36 | Improved |
| add search and reasoning tools to LLMs | LLM agents · Level 3 (Deep Search) events | score | Improved |
| add search tools to base LLM on Level 1 and 2 | Doubao-Seed1.6-Thinking base LLM · Level 1 and 2 events | score | No clear effect |
| wrap LLM in SmolAgent framework instead of Think&Search service | SmolAgent · overall score | score | Hurt |
| increase missing prediction rate from 1% to 20% (ablation) | Evaluation protocol · Monte Carlo simulation | standard deviation of average score | No clear effect |
| use Gemini-2.5-pro backbone in SmolAgent (ablation) | SmolAgent · Level 1 and 2 events | score | Improved |
Closest papers by meaning
- FutureSim: Replaying World Events to Evaluate Adaptive Agents (NeurIPS 2026 · similarity 0.89)
- UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon Scenarios (ICML 2026 · similarity 0.87)
- VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications (ICLR 2026 · similarity 0.86)
- ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory (NeurIPS 2026 · similarity 0.86)
- Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance (ICLR 2025 · similarity 0.86)
- Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments (ICLR 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
