{"version":1,"type":"story","url":"https://digestai.news/story/researchers-introduce-filingloop-for-sec-disclosure-review","json":"https://digestai.news/story/researchers-introduce-filingloop-for-sec-disclosure-review.json","markdown":"https://digestai.news/story/researchers-introduce-filingloop-for-sec-disclosure-review.md","slug":"researchers-introduce-filingloop-for-sec-disclosure-review","headline":"Researchers introduce FilingLoop for SEC disclosure review","summary":"A new research paper introduces FilingLoop, an interactive benchmark and self-evolving agent framework designed for corporate disclosure review and revision. The system is grounded in historical U.S. Securities and Exchange Commission correspondence, reconstructing 380 predominantly IPO review tasks from 96 companies. These tasks operate under distinct information constraints, requiring agents to discover unstated deficiencies, acquire missing company facts, and verify that revisions satisfy evidence-backed requirements.\n\nThe framework uses an evaluator separate from the acting agents to score final filings against 6,099 eligible requirements. It audits unsupported claims and harmful revisions while coupling iterative review with procedural learning across cases. This process converts requirement-level evaluation feedback into role-specific guidance without updating model weights, ensuring that updates only affect subsequent cases.\n\nOn the evaluated stream, this evolution strategy increased requirement fulfillment from 24.28% to 27.96% and full comment resolution from 16.90% to 20.75%. This improvement came with a 5.8% increase in total cost compared to a fixed-policy variant. FilingLoop aims to provide requirement-level feedback for procedures used in later review tasks, addressing limitations in existing financial question-answering evaluations.","keyPoints":["FilingLoop reconstructs 380 IPO review tasks from 96 companies using historical SEC correspondence.","An independent evaluator scores filings against 6,099 eligible requirements to audit claims.","Procedural learning increased requirement fulfillment from 24.28% to 27.96% without weight updates."],"whyItMatters":"This research advances AI agents' ability to handle complex, interactive financial compliance tasks. By demonstrating procedural learning without weight updates, it offers a scalable approach for automating rigorous corporate disclosure reviews.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["SEC"],"models":["FilingLoop"],"people":[]},"firstPublishedAt":"2026-10-30T04:00:00Z","updatedAt":"2026-10-30T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision","url":"https://arxiv.org/abs/2610.37905","publishedAt":"2026-10-30T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers introduce FilingLoop for SEC disclosure review\", 30 October 2026, https://digestai.news/story/researchers-introduce-filingloop-for-sec-disclosure-review","publisher":"Digest AI","title":"Researchers introduce FilingLoop for SEC disclosure review","datePublished":"2026-10-30T04:00:00Z","url":"https://digestai.news/story/researchers-introduce-filingloop-for-sec-disclosure-review"},"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"}