Independent by design · no pay-to-rank placements  · How we evaluate tools →
Anclum Submit
C

chensirui3/FIling-agent

Independent directory — not the official site. Details below come from the project's public repository.

Research agent that answers analyst questions from SEC filings using the XBRL API, filing search and a calculator.

Before you install: no copy-paste command · license MIT · link reachable

First step: nothing runnable here yet - start from the repository: https://github.com/chensirui3/FIling-agent

updated 2026-11-15
View on GitHub ↗Link checked 2026-11-17 · HTTP 200 · opens the vendor's own site
Star count
0 ★ · chensirui3/FIling-agent · read from the GitHub search API · (checked 2026-11-19 20:00:48)
Source
read directly from its GitHub page · type: open-source project
Harvest history
first seen 2026-11-15 · last seen 2026-11-20 · seen 6× · listed by 2 sources
Score
score 203 · 2 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Open Source. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository chensirui3/FIling-agent;first catalogued 2026-11-15;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.
README excerpt (English, untranslated) · Read the full README on GitHub →

# Filing Research Agent

Excerpted from the repository README (abridged)

An agent that answers analyst questions about US public companies, such as "What is 3M's FY2018 capital expenditure?" or "Does 3M have a healthy quick ratio in Q2 FY2023?". It uses the SEC's XBRL financial-data API, search over filing text, and a calculator. It is graded on the open-source sample of FinanceBench.
The evaluation is the core of the project:
component metrics (retrieval recall, XBRL coverage)
attribution of each failure to retrieval, table reading or arithmetic
before/after scores with confidence intervals for every fix
The tools are also exposed as an MCP server.
> Status: complete. Headline results are below; docs/RESULTS.md has every run and docs/ERROR_ANALYSIS.md every failure.
## Results
The frozen system is Claude Opus 5.5 at medium effort, with filing search, page reading, SEC XBRL facts and a calculator. Each row is one run; 95% Wilson intervals are in parentheses.
| Evaluation | Full agent |
| FinanceBench dev (50 questions) | 96% (86–99%) |
| FinanceBench test (100) | 85% (76.7–90.7%); 88% after correcting 2 wrong golds and a judge error |
| Fresh benchmark: filings published after the model's training cutoff (114) | 100% (96.7–100%) |
| Fresh hard tier: segment figures, two-year changes, ratios without formulas (75) | 94.7% (87.1–97.9%); 98.7% counting the readings 3 ambiguous questions allowed |
A memorization check ran the same model closed book, with no tools and no documents, once on each kind of question:
| Memorization check | Closed book |
| FinanceBench dev (50 questions) | 80% |
| Fresh benchmark (114) | 0% (all refusals) |
FinanceBench is largely memorized. With no documents, the model answers 80% of dev questions, but none about filings published after its training cutoff. The fresh benchmark (docs/FRESH.md) is built from 38 post-cutoff 10-Ks and 10-Qs, with golds taken from the filings' own XBRL tags and checked against the SEC API.
The agent's accuracy is research, not recall. It scores 100% on the post-cutoff questions. It uses the XBRL API only when the figure exists nowhere else (23 of 25 two-year-change questions, against 2 of 114 in the first tier).
The SEC API alone answers most metric questions. The agent answered 34 of FinanceBench's 50 metric questions correctly without opening a filing, a lower bound on what the XBRL data covers.
Almost every failure is on the question side. Of 21 failures in 339 questions, 2 are agent errors (both used a source for the wrong period). The rest are unstated definitions, judgment calls, ambiguous questions, wrong golds and one judge error. There are no retrieval, table-reading or arithmetic failures.
The grading holds up. A blind human check of 40 judge verdicts found no lenient ones (32 of 32 "correct" verdicts agreed). Where the two differed, the judge had been the stricter.
The one measured fix was rejected. A prompt change targeting the period error fixed it, but dev dropped 96% → 90% on three judgment questions (p = 0.25). The pre-registered rule rejected it, and the negative result is reported.
The baseline ladder on dev shows where the accuracy comes from. Tools add 12 to 16 points over memory, a single search without follow-up does worse than memory, and the full agent is within one question of being handed the evidence pages (docs/RESULTS.md has the paired tests).
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[![Listed on Anclum](https://anclum.com/badge/listed.svg)](https://anclum.com/en/s/chensirui3-filing-agent/)
Source
github · https://github.com/chensirui3/FIling-agent
Browse by field
Open source
Listed by
2 independent sources
added
today

More entries

All 1,875 →

Filed under

Every tag opens the full list for that filter. Counts are the live catalogue figures.

Browse all fields →

← Back to index