SPIRE · Agentic Research Directory

SPIRE

SPIRE coordinates seven scholarly agents that retrieve and compare primary passages, bind claims to evidence, and request further retrieval through bounded reflection. Its author study covers classical Chinese and Latin scholarship; citation recovery and essay ratings do not establish interpretive truth. The linked repository returned 404, so code availability and experiment-version parity remain unverified.

L3Multi-step tool-using agentic workflow Source Preprint (not peer-reviewed) Outcome Author-reported

Evidence & verification

Source level

Preprint (not peer-reviewed)
Grounded in a preprint that had not completed peer review at the time the source was checked.

Outcome verification

Author-reported
Outcomes are reported by the team that built the system. The entry is source-checked against the team's own publications; not independently reproduced.

Sources checked

2026-10-19 (UTC)

Checked source version: arXiv2605.30947v4;31August2026. Claims refer to this manuscript snapshot; final journal/proceedings version parity was not verified. Author-reported; independent replication not established in this review.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (1)

Research applicability

Documented humanities research workflow, with source-version and evaluation limits retained.

Getting started

Read the primary manuscript and its limitations first. Check implementation access and terms separately; this review did not run an installation, API call to a research system, or experiment.

Maintenance

Source snapshot checked 2026-10-19. Current availability and experimental version parity are separate claims.

License

Research code/data/manuscript terms require separate verification; repository metadata alone is not a reuse clearance.

Workflow & human oversight

L3 applies only to the corpus- and question-bounded evidence-grounded scholarship workflow. A user supplies a classical-text corpus, schema and question. Scholars retain interpretive judgement; blind human ratings are within the author study, not an installed approval mechanism. Seven roles retrieve, compare and bind evidence; reflection may request further retrieval. Reflection stops when its review passes or at two rounds. Citation recovery and study ratings do not certify historical interpretation or replace expert source judgement.

Workflow level is not an evidence score; higher is not better evidence.

Approach

Researcher supplies corpus/schema/question; seven scholarly roles share evidence, retrieve passages/graphs/clusters, bind claims and reflect with at most two retrieval rounds. Researchers retain final interpretation.

Outcomes (as reported by the originating team)

Author evaluation:406papers; full-pool EvidenceR44.3% versus ReAct30.0%, whereas EvidenceR@10=24.0%. Recall is paper-macro, using quotation/locator/embedding-match criteria. Two human experts and two LLM judges rate100stratifiedpapers, not all406.

Limitations

Chinese/Latin textual corpora only; citation recovery is not unique interpretive truth. Translation, scope and locus failures remain. Human ratings are within the author study, not independent replication. Dataset redistribution is restricted/derived; raw texts are not promised.

Reproducibility

Author-reported; independent replication not established in this review. Documentary review only; no candidate code, model, simulation or experiment was executed. A public repository or result artifact is not proof of replication.

Adoption requirements

Untested suggestion: inspect the pinned sources and validate data, evaluator assumptions, implementation availability and researcher controls before planning a bounded trial. No setup or trial was executed.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.