ROUND 366 — Agentsensus: selected messages, unpublished event logs
Reviewed: 2026-09-06 UTC

ASSESSMENT
New Chinese-documented story-world simulation project with selected interaction excerpts and a substantial paper artifact. It is a controlled simulation lead, not evidence of a free-running public community. Raw event logs and checkpoints are deliberately excluded. Chinese documentation supports language relevance; operator nationality and laboratory affiliation remain unverified.

PIN / SCOPE
https://github.com/impanyu/agentsensus
Default branch master; initial request to commits/main returned422, resolved by reading repository metadata.
Pinned c58f4b0ed2b29e403a04f0e8ac9d93d09fb96506
Complete recursive tree:287 entries, truncated=false.
README calls the framework AgentSociety; the paper calls it Agentsensus. Do not conflate this repository with other projects named AgentSociety.
Seven selected source blobs were fetched and verified against Git blob SHA1. No investigated scripts, model calls or installation instructions were executed.

WHAT IS ACTUALLY PUBLISHED
paper/excerpts.tex contains16 selected say-message examples: four memory backends across Three Kingdoms, Red Chamber, Hamlet and a Russia–Ukraine simulation. It supplies round numbers, fictional/simulated speakers and recipients, and translations for Chinese examples. It explicitly characterizes its comparative reading as observation on selected excerpts rather than measurement. No complete reply chains were recovered.
These include procedural coordination, requests for confirmation and status updates. Simulated geopolitical actors are not real officials; their dialogue is not evidence of real-world communications. Literary role names are not identities of independent public bots.
The full tree contains docs/index.html (4,195,712 bytes), LaTeX draft files, figures and generated number tables. The HTML body was not audited this round; file presence alone does not establish the underlying run data or results.

EXPLICIT DATA BOUNDARY
REPRODUCE.md says the repository carries the method and built paper, not run stores, checkpoints, event logs or scored results. It describes regenerating those through paid model calls and distinguishes method replication from exact numerical reproduction. Reported models are gpt-5-mini and text-embedding-3-small; labels are publisher claims, not provider-authenticated receipts.
.gitignore excludes runs/ and generated memory stores. The complete tree contains no events.jsonl or checkpoint.json paths. Therefore the documented ability to save checkpoints does not mean a published checkpoint corpus exists.
The reproduction guide says several continuation-quality scores operate on LLM-rendered screenplays, whereas goal and ablation scoring use event logs. These are different evidence layers: rendered prose should not be treated as raw dialogue without a source-event join. This round inspected documentation and excerpts, not the implementation of every metric.

SCHEDULING / SCALE LIMITS
README describes a tick barrier: decisions use the start-of-tick state, actions are applied in stable agent order, and messages arrive on a later tick. Environments and information carriers can use rule/retrieval backends rather than model decisions. Thus a world entity count cannot automatically be read as an equal number of concurrent LLM agents.
Longer horizons are described as resumed experiments. They are not evidence of calendar-long unattended operation. No simulation was started here.

ATTRIBUTION LIMIT
paper/main.tex is explicitly a draft using an ICLR template, with placeholder author/department/institution/email. Neither acceptance nor a named institutional affiliation was verified. The template itself is not publication evidence. No connection to the original escaped-actor hunt is established.

OTHER NEW DISCOVERY CANDIDATES
https://atomclub.cn/ advertises a human/agent community in search results, but the web reader returned zero extracted lines. It needs ordinary-browser inspection before any claim about actual participants or seeded content.
https://github.com/Ninefoldatwill/homestream is a separate Chinese-language local multi-agent framework candidate; runtime evidence not yet audited.
https://forum.trae.cn/t/topic/95443 describes Kook Agent, a community-bot-based supervisor/worker project; public output not yet audited.
Search also returned eco-agent, already present in round121: avoid treating that as a fresh discovery. AgentPanel is likewise already investigated in303–304.

NEXT
Prioritize actual community interactions on the new site and inspect whether any public run bundle is linked from Agentsensus's built paper. A missing raw dataset should not cause us to count selected excerpts as full runtime evidence or rerun paid experiments as a substitute for observing the publisher's activity.

PRESERVATION
366-private: repo/commit/tree metadata, README, reproduction guide, selected paper files, .gitignore and blob-checks.json. Public read-only research; no credentials, contacts, registration or tasks. Analytical report published separately from private source captures.