Language scope correction: raw English phrases and actor attribution
Reviewed 2026-09-05 UTC

The investigation target is agents associated with Chinese labs or operators, independent of the language in which they reason, search, code or publish. Raw English phrases on global websites and GitHub are explicitly in scope. Chinese-language traces are one search channel, not the definition of the target.

The user clarified that the discussion concerned the raw English phrase and supplied comments challenging a Chinese-only search assumption and the literal translation of “agent” as 代理. This correction affects both search coverage and terminology. For AI-agent concepts, 智能体 and 多智能体 are useful Chinese terms; 代理 is ambiguous and often means proxy. Preserve proxy terms when investigating network tooling, but do not mistake every proxy result for an AI-agent result.

Report 008 already documented why language or website geography cannot be a gate: Tongyi's published research environment uses Google and Jina, while DeepSeek's technical report explicitly describes multilingual search-task construction. Kimi and GLM also distinguish simulated tool environments from real coding/search environments. Those are capability and task-distribution observations, not attribution of a public artifact.
Source review:
http://178.105.23.35:8090/china/reports/008-capability-hypotheses.txt
Tongyi environment description:
https://arxiv.org/html/2510.24701v1#A4
DeepSeek agent-task description:
https://arxiv.org/html/2512.02556v1#S3.SS2.SSS3

The supplied discussion also asserted that DeepSeek performs coding reasoning mostly in English. This investigation has not measured or independently established that frequency claim. It is unnecessary for the scope correction: plausible English activity is enough to require English searches. Do not elevate the comment into a verified empirical result.

Practical search implications:
- Keep original English strings intact for exact-match searches; do not replace them with a Chinese translation. When an exact string is provided, search that string before using translated expansions.
- Include global public websites and GitHub. Inspect dated issues, discussions, code/tool definitions, model reports and linked artifacts when relevant. An official agent repository demonstrates capabilities or implementation details; it does not establish an escaped swarm.
- Search structural behavior as well as labels: repeated reference-link experiments, scratch-memory-like sequences, distinctive identifiers reused across surfaces, and coherent dates. A generic English “agent” or “test” string remains weak evidence.
- Separate language, model identity, operator identity, execution location and hosting provider. None determines all the others.
- Preserve the existing evidence standard: dated source verification, cross-surface coherence, alternative explanations, and independent attribution. Commercial tools, tutorials, ordinary coding tests, spam and post-disclosure imitation remain alternative explanations.

Operational snapshot: all 112 initially scheduled research tasks have returned outputs (72 initial and 40 follow-up). The latest follow-up runner reports completion at 2026-09-05T11:13:46Z with zero harness errors. Eight additional raw-English/GitHub tasks were subsequently launched, bringing planned coverage to 120 tasks; they are a separate wave from the completed 112. Returned outputs remain unverified unless separately reviewed; this is not a claim that all relevant surfaces were reachable or that the search is exhaustive.

The website now explicitly describes English/global/GitHub coverage and the Chinese terminology distinction. The continuation handoff records the same scope correction and completed task count. Working assessment remains zero confirmed Chinese actors; no candidate was promoted by changing the search vocabulary.