mlsanityData to 7 Oct 2026

Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs

arXiv 2604.18576 ↗First posted 20 Apr 2026cs.AIcited by 9

On the map: LLM agents and tool use → Financial trading and forecasting agents

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.

Key facts. Cited by 9 papers in the map (data through 7 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.

Builds on

31 of 60 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains18 Jan
  2. 2025FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction16 Aug

Other references · 29

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  3. 2024Approaching Human-Level Forecasting with Language Modelscited by 102
  4. 2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 66
  5. 2022Forecasting Future World Events with Neural Networkscited by 63
  6. 2026AutoHarness: improving LLM agents by automatically synthesizing a code harnesscited by 63
  7. 2024Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspectivecited by 51
  8. 2025Bayesian Teaching Enables Probabilistic Reasoning in Large Language Modelscited by 36
  9. 2025LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arenacited by 36
  10. 2025Prompt-to-Leaderboardcited by 27
  11. 2025Time-R1: Towards Comprehensive Temporal Reasoning in LLMscited by 23
  12. 2025Outcome-based Reinforcement Learning to Predict the Futurecited by 21
17 more
  1. 2025Scaling Open-Ended Reasoning to Predict the Futurecited by 19
  2. 2025Proper scoring rules for estimation and forecast evaluationcited by 18
  3. 2024Can Language Models Use Forecasting Strategies?cited by 13
  4. 2024OpenEP: Open-Ended Future Event Predictioncited by 11
  5. 2026Future-as-Label: Scalable Supervision from Real-World Outcomescited by 11
  6. 2026PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Datacited by 11
  7. 2026Prediction Arena: Benchmarking AI Models on Real-World Prediction Marketscited by 10
  8. 2025AIA Forecaster: Technical Reportcited by 9
  9. 2026Intrinsic Credit Assignment for Long Horizon Interactioncited by 9
  10. 2024Reasoning and Tools for Human-Level Forecastingcited by 7
  11. 2026Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoffcited by 6
  12. 2024BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modelingcited by 5
  13. 2025Prompt Engineering Large Language Models' Forecasting Capabilitiescited by 5
  14. 2026FinTradeBench: A Financial Reasoning Benchmark for LLMscited by 5
  15. 2026TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systemscited by 5
  16. 2026Bayesian Orchestration of Multi-LLM Agents for Cost-Aware Sequential Decision-Makingcited by 4
  17. 2025Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Askingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 9.

9 papers.

  1. 2026FutureSim: Replaying World Events to Evaluate Adaptive Agentscited by 7
  2. 2026Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecastingcited by 3
  3. 2026OracleProto: A Reproducible Framework for Benchmarking LLM Native Forecasting via Knowledge Cutoff and Temporal Maskingcited by 2
  4. 2026Who Checks the Citations? Benchmarking Legal Hallucination Detectioncited by 2
  5. 2026LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecastingcited by 1
  6. 2026BALAR : A Bayesian Agentic Loop for Active Reasoningcited by 0
  7. 2026Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agentscited by 0
  8. 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applicationscited by 0
  9. 2026Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting
  2. 2026WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning
  3. 2026CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting
  4. 2026KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
  5. 2026When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
  6. 2025TimeCopilot
  7. 2026Agentic Time Machine as an Infrastructure for Future-Event Forecasting
  8. 2026Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting