# Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis

arXiv: https://arxiv.org/abs/2607.25554 · HTML: https://mlsanity.com/paper/2607.25554/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Time series reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Placed in

- LLM reasoning / [Time series reasoning](https://mlsanity.com/lr/time-series-reasoning/)
- Synthetic data and self-improvement for LLMs / [Synthetic reasoning data and bootstrapping](https://mlsanity.com/synth/synthetic-reasoning-data-and-bootstrapping/)

## Builds on (most cited first, 23 of 23)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities](https://mlsanity.com/paper/2409.19839/) (2024)
- [Forecasting Future World Events with Neural Networks](https://mlsanity.com/paper/2206.15474/) (2022)
- [FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction](https://mlsanity.com/paper/2508.11987/) (2025)
- [DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL](https://mlsanity.com/paper/2509.10446/) (2025)
- [ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data](https://mlsanity.com/paper/2005.00792/) (2020)
- [LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena](https://mlsanity.com/paper/2510.17638/) (2025)
- [LongCat-Flash-Thinking-2601 Technical Report](https://mlsanity.com/paper/2601.16725/) (2026)
- [MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification](https://mlsanity.com/paper/2603.15726/) (2026)
- [Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution](https://mlsanity.com/paper/2509.25301/) (2025)
- [Outcome-based Reinforcement Learning to Predict the Future](https://mlsanity.com/paper/2505.17989/) (2025)
- [MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks](https://mlsanity.com/paper/2602.22808/) (2026)
- [Future-as-Label: Scalable Supervision from Real-World Outcomes](https://mlsanity.com/paper/2601.06336/) (2026)
- [FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains](https://mlsanity.com/paper/2601.12259/) (2026)
- [PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation](https://mlsanity.com/paper/2504.01509/) (2025)
- [FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards](https://mlsanity.com/paper/2604.26733/) (2026)
- [Harnessing Pre-Resolution Signals for Future Prediction Agents](https://mlsanity.com/paper/2604.15719/) (2026)

## Abstract (arXiv)

Future event prediction carries broad social impact yet remains challenging. SOTA approaches augment LLMs with external agent frameworks whose predictive capability vanishes once the harness is removed. While recent Tool-Integrated Reasoning (TIR) internalizes deep search for multi-hop retrieval of facts, forecasting further demands temporal search and reasoning over historical trends and dynamic shifts. The key obstacle is data: historical queries induce temporal leakage that degrades forecasting into retrieval. Prior works either freeze information gathering with static observations, or rely on rejection sampling or unresolved fresh queries that discard vast amounts of data, degrading synthesis efficiency. We propose a time-truncation harness that enforces a temporal cut-off at every turn, enabling TIR-style sampling from historical events, reducing temporal leakage and reliance of rejection sampling or unsolved queries, increasing the sampling efficiency. We further build a large-scale corpus and a process-based metric and show that our harness naturally induces a broader temporal breadth of search and raises the proportion of high-quality data, further increasing the efficiency and reducing the reliance on complex rubrics. Distillation experiments show that students trained on harness-intervened data achieve the best performance, demonstrating harness-assisted model evolving that turns higher quality temporal search and reasoning data into a parametric advancement of the students.