Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs

• URL: http://arxiv.org/abs/2604.18576v2
• Date: Tue, 21 Apr 2026 16:42:06 GMT
• Title: Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs
• Abstract summary: BLF (Bayesian Linguistic Forecaster) is an agentic system for binary forecasting.<n>On 400 backtesting questions from the ForecastBench leaderboard, BLF outperforms all the top public methods.
• Score: 1.7470133607730627
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present BLF (Bayesian Linguistic Forecaster), an agentic system for binary forecasting that achieves state-of-the-art performance on the ForecastBench benchmark. The system is built on three ideas. (1) A linguistic belief state: a semi-structured representation combining numerical probability estimates with natural-language evidence summaries, updated by the LLM at each step of an iterative tool-use loop. This contrasts with the common approach of appending all retrieved evidence to an ever-growing context. (2) Hierarchical multi-trial aggregation: running $K$ independent trials and combining them using logit-space shrinkage with a data-dependent prior. (3) Hierarchical calibration: Platt scaling with a hierarchical prior, which avoids over-shrinking extreme predictions for sources with skewed base rates. On 400 backtesting questions from the ForecastBench leaderboard, BLF outperforms all the top public methods, including Cassi, GPT-5, Grok~4.20, and Foresight-32B. Ablation studies show that the structured belief state is almost as impactful as web search access, and that shrinkage aggregation and hierarchical calibration each provide significant additional gains. In addition, we develop a robust back-testing framework with a leakage rate below 1.5\%, and use rigorous statistical methodology to compare different methods while controlling for various sources of noise.

Related papers

• Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation [4.947134980425439]
  We introduce branch-centric tokenization, a branch-aware representation that encodes connectivity directly in the sequence.<n>We also introduce view-augmented generation, a test-time augmentation procedure that applies axis-aligned rotations to the input mesh.<n> Experiments show that our method achieves better skeleton prediction accuracy than state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-09-05T18:28:35Z)
• Learning Auditable Classifier Models: Source-Disjoint Tree Ensembles [0.0]
  Predictive models in clinical and regulated settings must be accurate and fully auditable.<n>We introduce Residual Pattern Tree Ensemble (RPTE), a three-stage learning approach.<n>RPTE builds on three key principles: bounded feature budget, source disjointness, and separate coefficient estimation.
  arXiv  Detail & Related papers  (2026-08-16T12:56:49Z)
• Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning [14.640786318359709]
  Branching Policy Optimization (BPO) is a sandbox-native RL algorithm that snapshots the sandbox at high-entropy decision points along a backbone trajectory.<n>We prove this estimator is unbiased and has strictly lower variance than the trajectory-level baseline.<n>BPO improves success by 3.6--6.1 absolute points over GRPO and RLOO at matched compute, halves gradient-norm variance, and matches the best baseline using 38% fewer policy updates.
  arXiv  Detail & Related papers  (2026-07-15T09:37:36Z)
• Learn from your own latents and not from tokens: A sample-complexity theory [53.5821824211418]
  We study networks trained to predict their emphown latent representations of related views or masked regions.<n>We show that latent prediction achieves this with a number of samples emphconstant in $L$, up to logarithmic factors.<n>This suggests that explicit stacking such as H-JEPA is largely redundant.
  arXiv  Detail & Related papers  (2026-05-26T22:16:42Z)
• DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles [5.647839536820347]
  We introduce DiscoUQ, a framework that extracts and leverages the structure of inter-agent disagreement to produce well-calibrated confidence estimates.<n>DiscoUQ-LLM achieves an average AUROC of 0.802, outperforming the best baseline.<n>The learned features generalize across benchmarks with near-zero performance degradation.
  arXiv  Detail & Related papers  (2026-03-21T23:24:12Z)
• PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution [2.28438857884398]
  LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows.<n>We introduce PRECEPT, a unified framework for test-time adaptation with three tightly coupled components.
  arXiv  Detail & Related papers  (2026-03-10T13:16:45Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Learning Discrete Bayesian Networks with Hierarchical Dirichlet Shrinkage [52.914168158222765]
  We detail a comprehensive Bayesian framework for learning DBNs.<n>We give a novel Markov chain Monte Carlo (MCMC) algorithm utilizing parallel Langevin proposals to generate exact posterior samples.<n>We apply our methodology to uncover prognostic network structure from primary breast cancer samples.
  arXiv  Detail & Related papers  (2025-09-16T17:24:35Z)
• Foundation Models for Demand Forecasting via Dual-Strategy Ensembling [11.926658499983446]
  We propose a unified ensemble framework that enhances the performance of foundation models for sales forecasting in real-world supply chains.<n>Our method combines two complementary strategies: (1) Hierarchical Ensemble (HE), which partitions training and inference by semantic levels to capture localized patterns; and (2) Architectural Ensemble (AE), which integrates predictions from diverse model backbones to mitigate bias and improve stability.
  arXiv  Detail & Related papers  (2025-07-29T17:56:38Z)
• Syntactic Control of Language Models by Posterior Inference [53.823006836309695]
  Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability.<n>We argue that sampling algorithms based on the posterior inference can effectively enforce a target constituency structure during generation.<n>Our approach combines sequential Monte Carlo, which estimates the posterior distribution by sampling from a proposal distribution, with a syntactic tagger that ensures that each generated token aligns with the desired syntactic structure.
  arXiv  Detail & Related papers  (2025-06-08T14:01:34Z)
• Confidence Diagram of Nonparametric Ranking for Uncertainty Assessment in Large Language Models Evaluation [20.022623972491733]
  Ranking large language models (LLMs) has proven to be an effective tool to improve alignment based on the best-of-$N$ policy.<n>We propose a new inferential framework for hypothesis testing among the ranking for language models.
  arXiv  Detail & Related papers  (2024-12-07T02:34:30Z)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval [139.21955930418815]
  Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
  arXiv  Detail & Related papers  (2023-09-29T09:41:19Z)
• Unifying Language Learning Paradigms [96.35981503087567]
  We present a unified framework for pre-training models that are universally effective across datasets and setups. We show how different pre-training objectives can be cast as one another and how interpolating between different objectives can be effective. Our model also achieve strong results at in-context learning, outperforming 175B GPT-3 on zero-shot SuperGLUE and tripling the performance of T5-XXL on one-shot summarization.
  arXiv  Detail & Related papers  (2022-05-10T19:32:20Z)
• Parameter Decoupling Strategy for Semi-supervised 3D Left Atrium Segmentation [0.0]
  We present a novel semi-supervised segmentation model based on parameter decoupling strategy to encourage consistent predictions from diverse views. Our method has achieved a competitive result over the state-of-the-art semisupervised methods on the Atrial Challenge dataset.
  arXiv  Detail & Related papers  (2021-09-20T14:51:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.