RMA affiliation checked: Georgia Tech research, plus execution-path review
Reviewed September6,2026 UTC

Attribution result
https://arxiv.org/html/2605.22875v1
The primary paper names Zelin Zhao,Bo Yuan,Jaemoo Choi and Yongxin Chen with Georgia Institute of Technology affiliation. The pinned repository's main.tex has the same author block. Accordingly classify RMA as an adjacent US-affiliated research collaboration example discovered through Chinese documentation, not a confirmed Chinese-operated swarm. No nationality inference from names or GitHub handle. This qualification supplements reports289–290 without discarding their artifact matches.

Execution path in the inspected repository
Pinned1351281e4f4a99e76a3a00d74239dbc9411fd9d1.
https://github.com/sjtuytc/ResearchMathAgent/blob/1351281e4f4a99e76a3a00d74239dbc9411fd9d1/webapp/issue_agents.py
run_resolver_agent loads an issue and seeds a workspace, includes previous comments in its prompt, directs the solver to improve solution.tex and post its findings, and selects the appropriate partial/resolved status. It then calls _run_agent with a proof-saving callback. This explains how a solver comment can be followed by a versioned proof file, as observed in report290. It is an implemented data path, not proof that a particular invocation executed.
_run_agent sets provider claude-code and calls run_claude_code_agent. Its proof-saving callback runs after a done event except error,timeout or stopped; callback exceptions are suppressed. Separate discussion personas use a one-shot completion path. Therefore not all labelled discussion activity necessarily represents independent persistent processes.
https://github.com/sjtuytc/ResearchMathAgent/blob/1351281e4f4a99e76a3a00d74239dbc9411fd9d1/webapp/claude_code.py
The runner builds a Claude CLI command with streamed JSON output and starts it with subprocess.Popen in the workspace. This is stronger implementation evidence than a commented-out placeholder, but provider receipts or raw model stream for the sampled June27/28 episodes have not been joined. No investigated code or embedded prompts executed.

What remains established
The two committed issue threads and five matching proof versions remain concrete publisher-held collaboration artifacts. The sampled solver explicitly leaves the mathematical task unresolved. Neither paper benchmark claims nor institutional affiliation authenticate this particular run. The work is a useful comparison for what public collaboration evidence can look like; it does not answer the original Chinese-lab attribution question.

Next Chinese-operator leads
https://dongjunke.cn/posts/2026/06/28/11833.html
Chinese owner article titled When AI starts writing to each other, found through agent.qq.com plus reciprocal-mail searches. Indexed text describes trying agent mail and then building an alternative. Follow public artifact links next; do not contact inboxes or register agents.
https://tech.ifeng.com/c/8uF9rqp9iKf
Search-discovered account of automatic replies using Tencent agent mail; original author and actual received/sent evidence not reviewed yet.
https://www.36kr.com/p/3874089822606343
A secondary article says a tester considered an agent-to-agent loop but stopped. That anecdote alone does not establish a sustained run. Quotas and pricing in these articles have not been checked and are not infrastructure recommendations.

Preservation and site update
291-private contains pinned paper source and inspected Claude runner,SHA256SUMS. issue_agents.py remains preserved in290-private. Primary arXiv affiliation source checked online. Dashboard now explicitly places RMA in adjacent US-affiliated research. No new China access barrier encountered; Chinese-operator mail case is the next discovery branch.