{"version":1,"type":"story","url":"https://digestai.news/story/researchers-release-paws-dataset-for-policy-driven-financial-agent-sim","json":"https://digestai.news/story/researchers-release-paws-dataset-for-policy-driven-financial-agent-sim.json","markdown":"https://digestai.news/story/researchers-release-paws-dataset-for-policy-driven-financial-agent-sim.md","slug":"researchers-release-paws-dataset-for-policy-driven-financial-agent-sim","headline":"Researchers release PAWS dataset for policy-driven financial agent simulation","summary":"A new dataset called PAWS (Policy-driven Agentic World Simulation) has been published on arXiv, offering a structured resource for simulating how financial policies propagate through markets and stakeholders. The dataset covers 36 verified U.S. financial and economic policy episodes, 12,727 policy-linked news records, and 65,291 source-grounded stakeholder actions. Each action is linked to supporting news and encoded in a multi-layer event frame that captures interaction mode, financial-action family and subtype, semantic attributes, and mappings to external taxonomies. Entities are resolved to normalized organizations, and actions are aligned with daily market-return context to enable simulation replay.\n\nQuality checks on 2,522 stratified action samples showed 89.4% initial agreement between independent AI and human reviewers on interaction mode, with disagreements adjudicated afterward. Case studies on the 2008 short-selling ban and 2001 decimalization demonstrate the dataset's ability to recover documented policy timelines and market patterns. A replay study also found that high overall accuracy can mask failures to detect rare stakeholder actions, highlighting action timing and calibration as key challenges. The authors position PAWS as an auditable substrate for evaluating agent influence, policy-response cascades, and action-outcome alignment in historically grounded financial simulations.","keyPoints":["PAWS dataset covers 36 U.S. policy episodes, 12,727 news records, 65,291 stakeholder actions","AI and human reviewers reached 89.4% agreement on interaction mode across 2,522 samples","Case studies on 2008 short-selling ban and 2001 decimalization validate timeline recovery"],"whyItMatters":"PAWS provides a historically grounded, auditable dataset for testing how AI agents simulate policy propagation and stakeholder responses in financial markets, addressing a gap in temporally aligned, multi-source simulation data.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-09-25T04:00:00Z","updatedAt":"2026-09-25T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"PAWS: Policy-driven Agentic World Simulation","url":"https://arxiv.org/abs/2609.28547","publishedAt":"2026-09-25T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers release PAWS dataset for policy-driven financial agent simulation\", 25 September 2026, https://digestai.news/story/researchers-release-paws-dataset-for-policy-driven-financial-agent-sim","publisher":"Digest AI","title":"Researchers release PAWS dataset for policy-driven financial agent simulation","datePublished":"2026-09-25T04:00:00Z","url":"https://digestai.news/story/researchers-release-paws-dataset-for-policy-driven-financial-agent-sim"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}