# Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs

arXiv: https://arxiv.org/abs/2604.18576 · HTML: https://mlsanity.com/paper/2604.18576/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 30 of 31)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Approaching Human-Level Forecasting with Language Models](https://mlsanity.com/paper/2402.18563/) (2024)
- [AutoHarness: improving LLM agents by automatically synthesizing a code harness](https://mlsanity.com/paper/2603.03329/) (2026)
- [Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy](https://mlsanity.com/paper/2402.19379/) (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)
- [Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective](https://mlsanity.com/paper/2406.00793/) (2024)
- [LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena](https://mlsanity.com/paper/2510.17638/) (2025)
- [Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models](https://mlsanity.com/paper/2503.17523/) (2025)
- [Prompt-to-Leaderboard](https://mlsanity.com/paper/2502.14855/) (2025)
- [Time-R1: Towards Comprehensive Temporal Reasoning in LLMs](https://mlsanity.com/paper/2505.13508/) (2025)
- [Outcome-based Reinforcement Learning to Predict the Future](https://mlsanity.com/paper/2505.17989/) (2025)
- [Scaling Open-Ended Reasoning to Predict the Future](https://mlsanity.com/paper/2512.25070/) (2025)
- [Proper scoring rules for estimation and forecast evaluation](https://mlsanity.com/paper/2504.01781/) (2025)
- [Can Language Models Use Forecasting Strategies?](https://mlsanity.com/paper/2406.04446/) (2024)
- [PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data](https://mlsanity.com/paper/2604.14199/) (2026)
- [OpenEP: Open-Ended Future Event Prediction](https://mlsanity.com/paper/2408.06578/) (2024)
- [Future-as-Label: Scalable Supervision from Real-World Outcomes](https://mlsanity.com/paper/2601.06336/) (2026)
- [Prediction Arena: Benchmarking AI Models on Real-World Prediction Markets](https://mlsanity.com/paper/2604.07355/) (2026)
- [AIA Forecaster: Technical Report](https://mlsanity.com/paper/2511.07678/) (2025)
- [FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains](https://mlsanity.com/paper/2601.12259/) (2026)
- [Intrinsic Credit Assignment for Long Horizon Interaction](https://mlsanity.com/paper/2602.12342/) (2026)
- [Reasoning and Tools for Human-Level Forecasting](https://mlsanity.com/paper/2408.12036/) (2024)
- [Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoff](https://mlsanity.com/paper/2601.13717/) (2026)
- [TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems](https://mlsanity.com/paper/2604.05364/) (2026)
- [BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling](https://mlsanity.com/paper/2406.05516/) (2024)
- [Prompt Engineering Large Language Models' Forecasting Capabilities](https://mlsanity.com/paper/2506.01578/) (2025)
- [FinTradeBench: A Financial Reasoning Benchmark for LLMs](https://mlsanity.com/paper/2603.19225/) (2026)
- [Bayesian Orchestration of Multi-LLM Agents for Cost-Aware Sequential Decision-Making](https://mlsanity.com/paper/2601.01522/) (2026)

## Built on by (most cited first, 10 of 10)

- [FutureSim: Replaying World Events to Evaluate Adaptive Agents](https://mlsanity.com/paper/2605.15188/) (2026)
- [Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting](https://mlsanity.com/paper/2605.27668/) (2026)
- [OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking](https://mlsanity.com/paper/2605.03762/) (2026)
- [Who Checks the Citations? Benchmarking Legal Hallucination Detection](https://mlsanity.com/paper/2606.21155/) (2026)
- [Diversity is the Strength of the AI Crowd](https://mlsanity.com/paper/2606.29661/) (2026)
- [LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications](https://mlsanity.com/paper/2608.23058/) (2026)
- [LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting](https://mlsanity.com/paper/2609.01337/) (2026)
- [BALAR : A Bayesian Agentic Loop for Active Reasoning](https://mlsanity.com/paper/2605.05386/) (2026)
- [Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents](https://mlsanity.com/paper/2607.03015/) (2026)
- [Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents](https://mlsanity.com/paper/2609.28876/) (2026)

## Abstract (arXiv)

We propose the Bayesian Linguistic Forecaster (BLF), which is a search-based ReAct style agent for (binary) forecasting that augments its context with a linguistic 'belief state', consisting of a probability estimate and a structured natural-language evidence summary. (The belief update is 'Bayesian-inspired' rather than exact Bayesian inference, although we do include a comparison to a more explicit Bayesian approach using LLM-elicited likelihood surrogates.) On 400 historical ForecastBench question-date instances, BLF has the highest overall Brier Index among the compared external agents, and is the only compared method to significantly outperform a crowd+empirical-prior baseline in terms of overall performance. Our backtesting framework combines date-aware search tools, leakage auditing, and paired comparisons for variance control to provide a rigorous empirical framework for comparing agentic forecasting systems.