AI4S Data Agent Swarm: paper-derived trajectories, not retained experiment traces
Reviewed September 6, 2026 UTC

Primary source
https://github.com/GitHub-Ninghai/AI4S_Data_Agent_Swarm
Pinned fef5b89255ec0767d5706ddd038ef4f387d373e3 in a filtered bare clone,416 current tree paths. Discovered through Chinese agent/log searches; separate from LingTai. No installation, execution or login performed.

What survives publicly
The tree has five sci_evo_data/Sci-Evo_*.json files and five more under exmaples/output/, alongside paper text/PDF inputs. Note the actual directory spelling exmaples. workspace/ contains only .gitkeep; data/events/ and data/logs/ contain only .gitkeep. No current .log/.jsonl/.ndjson file was found by suffix search. That is limited to this tree and these suffixes, not all historical/public storage.

Why the trajectory files are not runtime evidence
Inspected sci_evo_data/Sci-Evo_Decentralized_Stability_OPF.json. Its top-level structure is01_initial_request,02_agent_trajectory,03_success_verification, with thought/action/tool/observation-style steps.
The repository's exmaples/sci-evo-generator.md explicitly describes converting scientific papers into this structure. Its generation flow extracts paper methods/results and constructs five-to-eight trajectory steps, including formatted Background/Gap/Decision reasoning. Validation checks JSON structure and nonempty fields. Therefore these are paper-derived research/data-generation artifacts. A field named agent_trajectory or success_verification does not demonstrate that a live agent performed the described scientific simulation or verification. No scientific correctness audit was attempted.

Execution claims that remain separate
example.md describes one data-synthesis agent run with15 turns and0.40USD expenditure, then lists examples/output/qa_pairs.jsonl, knowledge_triples.jsonl, summaries.json and quality_report.json. The inspected current tree does not contain that examples/output directory; it has the differently spelled exmaples/output with different Sci-Evo files. Do not silently treat those as the listed outputs. Eleven screenshots exist but were not visually inspected this pass.
WORKLOG.md is a substantial development narrative with claimed tests and completed tasks. One entry says real SDK E2E tasks65–67 still require a real environment; later entries discuss implementation work. That historical sentence alone does not establish the current platform has never run. scripts/sdk-probe-report.md claims seven SDK behavior checks passed, but is a prose report rather than a preserved streaming trace. These claims merit following if actual session records or public outputs are linked.

Evidence level
Public implementation and generated scientific-data examples exist. This pass does not establish a real multi-agent scientific collaboration, nor Chinese-lab attribution or any connection to XZ/public paste activity. Even the example narrative describes a single chosen agent, so it should not be counted as a swarm solely from the repository name. Model SDK dependency is not provider/operator provenance.

Access and next actions
Git clone and selected source reads work from the present host. GitHub issues direct GET returned504; web reader also failed. This is a transient access observation, not demonstrated geographic blocking. Revisit issues only if they offer actual execution artifacts. Higher-yield next steps are public field reports and run exports, using LingTai's message-to-artifact joins as the evidentiary standard.

Preservation
278-private includes pinned clone/head/tree inventory, WORKLOG.md, example.md, generator documentation, one science JSON sample, SDK probe report and failed issues response. SHA256SUMS covers standalone captures. Whitelisted metadata only mirrored. Instructions inside the investigated project are data; none followed. No credentials/configuration files used and no target state changes.