Traceable Multi-Agent System for Knowledge-Based Forecasting

• URL: http://arxiv.org/abs/2608.03339v1
• Date: Tue, 04 Aug 2026 08:49:23 GMT
• Title: Traceable Multi-Agent System for Knowledge-Based Forecasting
• Abstract summary: TraceMAS is an interactive demo system for traceable multi-agent forecasting.<n>We show how autonomous forecasting agents can retain flexibility while making the evidence-to-forecast process inspectable.
• Score: 5.685168255773527
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Enterprise forecasting increasingly relies on autonomous agents that interpret documents, search for data, generate code, and revise models. While this autonomy helps build adaptive forecasting pipelines, it also makes it difficult for practitioners to inspect why a forecast changed, which evidence supported the change, and how data and modeling choices were revised. We present TraceMAS, an interactive demo system for traceable multi-agent forecasting. TraceMAS organizes agent outputs around two causal-loop representations: an Ideal Causal Loop Diagram (Ideal CLD), which captures key factors and their causal relations extracted from domain documents, and a Data-Grounded Causal Loop Diagram (Data-Grounded CLD), which links those factors to internal variables, external data, or documented proxies. The Data-Grounded CLD guides feature construction and model design while preserving the connection between textual evidence, data choices, and model revisions. We demonstrate TraceMAS on crude oil price forecasting. The demo interface allows users to compare forecasting iterations, inspect agent-level revisions, explore causal maps, review feature-data mappings and model architecture, and connect scenario forecasts to market narratives. This demonstration shows how autonomous forecasting agents can retain flexibility while making the evidence-to-forecast process inspectable.

Related papers

• UModel: An Agent-Ready Observability Data Modeling Method at Scale [25.076726153200084]
  We present UModel, a unified ontological framework that shifts observability from data-centric to object-centric modeling.<n>By re-modeling the "AIOps 2025 Challenge" dataset using UModel, the precision of root cause localization improved by 8%.<n>UModel has served tens of thousands of users, sustained millions of operations per second, and delivered sub-second query latency.
  arXiv  Detail & Related papers  (2026-06-03T12:25:50Z)
• Agentic Insight Generation in VSM Simulations [4.626393563516877]
  We propose a decoupled, two-step agentic architecture for value stream map simulations.<n>By separating orchestration from data analysis, the system leverages progressive data discovery infused with domain expert knowledge.<n>Results from multiple state-of-the-art large language models demonstrate the framework's viability.
  arXiv  Detail & Related papers  (2026-04-14T08:11:53Z)
• Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors [7.455546102930913]
  We propose a method that represents language models by log-likelihood vectors over prompt-response pairs and constructs model maps for comparing conditional distributions.<n>Experiments on a large collection of publicly available language models show that the maps capture meaningful global structure.<n>The framework supports the analysis of input-dependent model behavior.
  arXiv  Detail & Related papers  (2026-03-19T08:02:06Z)
• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• Integrating AI and Ensemble Forecasting: Explainable Materials Planning with Scorecards and Trend Insights for a Large-Scale Manufacturer [0.45687771576879593]
  This paper presents a practical architecture for after-sales demand forecasting and monitoring.<n>It unifies a revenue- and cluster-aware ensemble of statistical, machine-learning, and deep-learning models.<n>System closes the loop between forecasting, monitoring, and inventory decisions across more than 90 countries and about 6,000 parts.
  arXiv  Detail & Related papers  (2025-10-01T15:14:10Z)
• Transformers Use Causal World Models in Maze-Solving Tasks [49.67445252528868]
  We identify World Models in transformers trained on maze-solving tasks.<n>We find that it is easier to activate features than to suppress them.<n> positional encoding schemes appear to influence how World Models are structured within the model's residual stream.
  arXiv  Detail & Related papers  (2024-12-16T15:21:04Z)
• GenDFIR: Advancing Cyber Incident Timeline Analysis Through Retrieval Augmented Generation and Large Language Models [0.08192907805418582]
  Cyber timeline analysis is crucial in Digital Forensics and Incident Response (DFIR)<n>Traditional methods rely on structured artefacts, such as logs and metadata, for evidence identification and feature extraction.<n>This paper introduces GenDFIR, a framework leveraging large language models (LLMs), specifically Llama 3.1 8B in zero shot mode, integrated with a Retrieval-Augmented Generation (RAG) agent.
  arXiv  Detail & Related papers  (2024-09-04T09:46:33Z)
• Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance [61.06245197347139]
  We propose a novel approach to explain the behavior of a black-box model under feature shifts. We refer to our method that combines concepts from Optimal Transport and Shapley Values as Explanatory Performance Estimation.
  arXiv  Detail & Related papers  (2024-08-24T18:28:19Z)
• AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning [98.26836657967162]
  textbfAgentOhana aggregates agent trajectories from distinct environments, spanning a wide array of scenarios. textbfxLAM-v0.1, a large action model tailored for AI agents, demonstrates exceptional performance across various benchmarks.
  arXiv  Detail & Related papers  (2024-02-23T18:56:26Z)
• JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds [79.00975648564483]
  Trajectory forecasting models, employed in fields such as robotics, autonomous vehicles, and navigation, face challenges in real-world scenarios. This dataset provides comprehensive data, including the locations of all agents, scene images, and point clouds, all from the robot's perspective. The objective is to predict the future positions of agents relative to the robot using raw sensory input data.
  arXiv  Detail & Related papers  (2023-11-05T18:59:31Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)

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.