# Съответствие

Изследвания на регулаторно съответствие, прилагане на политики и одиторски следи за финансови ИИ системи

7 публикации [Вижте всички етикети](https://beancount.io/bg/bean-labs/research-logs/tags) [Обратно към всички публикации](https://beancount.io/bg/bean-labs/research-logs)

5 юли 2026 г. 6 минути четене

## [FinToolBench: Оценка на LLM агенти при реален финансов инструментариум](https://beancount.io/bg/bean-labs/research-logs/2026/07/05/fintoolbench-evaluating-llm-agents-real-world-financial-tool-use)

FinToolBench съчетава 760 реални финансови API инструмента с 295 изпълними заявки, за да оцени LLM агенти върху реални финансови задачи — разкривайки, че консервативният процент на извикване от 22,7% на GPT-4o води до по-високо качество на отговорите (CSS 0,670) от агресивния TIR от 87,1% на Qwen3-8B, докато несъответствието на намеренията надхвърля 50% при всеки тестван модел.

Mike Thrift

ai llm automation

5 юни 2026 г. 6 минути четене

## [Verifiably Safe Tool Use for LLM Agents: STPA Meets MCP](https://beancount.io/bg/bean-labs/research-logs/2026/06/05/verifiably-safe-tool-use-llm-agents-stpa-mcp)

STPA plus capability-enhanced MCP yields formal safety specs for LLM tool use, with Alloy proving no unsafe flows in a calendar case study.

Mike Thrift

ai llm security

3 юни 2026 г. 5 минути четене

## [FinAuditing: LLMs Score Under 14% on Real SEC XBRL Auditing Tasks](https://beancount.io/bg/bean-labs/research-logs/2026/06/03/finauditing-xbrl-taxonomy-benchmark-llm)

FinAuditing shows top LLMs hit just 13.86% on financial math verification of real SEC XBRL filings, capping what AI accounting tools can automate unaided.

Mike Thrift

llm ai financial-reporting

29 май 2026 г. 6 минути четене

## [AGrail: Adaptive Safety Guardrails for LLM Agents That Learn Across Tasks](https://beancount.io/bg/bean-labs/research-logs/2026/05/29/agrail-lifelong-agent-guardrail-adaptive-safety-detection)

AGrail's two-LLM guardrail cuts prompt injection attack success to 0% while preserving 95.6% of benign agent actions on Safe-OS.

Mike Thrift

ai llm security

28 май 2026 г. 6 минути четене

## [ShieldAgent: Verifiable Safety Policy Reasoning for LLM Agents](https://beancount.io/bg/bean-labs/research-logs/2026/05/28/shieldagent-verifiable-safety-policy-reasoning-llm-agents)

ShieldAgent hits 90.4% accuracy on agent attacks with 64.7% fewer API calls by using probabilistic rule circuits instead of LLM guardrails.

Mike Thrift

ai llm machine-learning

22 май 2026 г. 6 минути четене

## [AuditCopilot: LLMs for Fraud Detection in Double-Entry Bookkeeping](https://beancount.io/bg/bean-labs/research-logs/2026/05/22/auditcopilot-llm-fraud-detection-double-entry-bookkeeping)

AuditCopilot cuts journal entry fraud false positives from 942 to 12, but ablation shows the LLM mainly synthesizes Isolation Forest scores.

Mike Thrift

fraud-detection llm double-entry

21 април 2026 г. 6 минути четене

## [Конституционен ИИ за счетоводни агенти: RLAIF, правила за политиките и рискове от Гудхартинг](https://beancount.io/bg/bean-labs/research-logs/2026/04/21/constitutional-ai-harmlessness-from-ai-feedback)

Constitutional AI заменя ръчно етикетираните данни за вреди с AI обратна връзка, така че счетоводните агенти налагат правила без проверяващ за всяка транзакция.

Mike Thrift

ai machine-learning llm

[Започни безплатно→](https://beancount.io/sign-up/?next=%2Fledger%2F) [Документация](https://beancount.io/bg/docs)

## Where to look next

- [Sitemap](https://beancount.io/sitemap.xml) - all pages with hreflang alternates
- [LLMs index](https://beancount.io/llms.txt) - curated links for AI agents (also /llms-full.txt for full docs)
- [Documentation](https://beancount.io/docs) - every doc is also available as text/markdown via .md suffix or Accept negotiation
- [REST API reference](https://beancount.io/docs/api-reference) - interactive endpoints, schemas, authentication, and code samples
- [OpenAPI spec](https://beancount.io/openapi.json) - OpenAPI 3.1 spec for this website's public content endpoints; the product contract for ledger operations is at https://beancount.io/api-gateway/v1/openapi.json
- [GraphQL](https://beancount.io/graphql) - public, read-only content API over the blog and research logs (no credentials, no ledger data): 12 query fields over 23 types
- [MCP server](https://beancount.io/mcp) - Model Context Protocol at https://beancount.io/api-gateway/mcp
