FilingLoop：评估与演进企业信息披露审查 LLM Agent 的交互式基准
FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision
AI 导读
arXiv 论文提出 FilingLoop，一个面向企业披露文件审查与修订的交互式基准和自进化 Agent 框架，基于美国 SEC 历史函件重建了 96 家公司的 380 个以 IPO 为主的审查任务，由独立评估者依据 6,099 条合格要求打分并审计无依据陈述。
正文 · 原文
Abstract:Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabilities. We introduce \textbf{FilingLoop}, an interactive benchmark and a self-evolving agent framework for corporate disclosure review and revision. Grounded in historical U.S.\ Securities and Exchange Commission correspondence, FilingLoop reconstructs 380 predominantly IPO review tasks from 96 companies under distinct information constraints. An evaluator separate from the acting agents scores final filings and responses against 6,099 eligible requirements and audits unsupported claims and harmful revisions. Our framework couples iterative review and revision within each case with procedural learning across cases, converting requirement-level evaluation feedback into role-specific guidance without updating model weights. Updates affect only subsequent cases, allowing procedural adaptation to be assessed without retrying scored tasks. On the evaluated stream, evolution increases requirement fulfillment from 24.28\% to 27.96\% and full comment resolution from 16.90\% to 20.75\%, with a 5.8\% increase in total cost over the fixed-policy variant. FilingLoop connects the concerns an agent discovers with the company facts it obtains and the revisions it commits, providing requirement-level feedback for procedures used in later review tasks.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37905 [cs.AI] |
| (or arXiv:2610.37905v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37905 arXiv-issued DOI via DataCite |
Submission history
From: Wentao Zhang [view email]
[v1]
Tue, 27 Oct 2026 19:45:05 UTC (2,860 KB)
来源：arXiv cs.AI · arxiv.org