Early-career researcher applying LLMs to BT–FSM model transformation and AI agent exploration benchmarking
2
papers here
0
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
0
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-28) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
The output score is unavailable: OpenAlex shows h-index 0, i10-index 0, and just 3 works in the recent three-year window. This axis measures publication volume and consistency over time, and the current record is too sparse to assess.
Impact—
Impact cannot be scored: the snapshot carries no citation figures beyond h-index 0 and i10-index 0, and both catalog papers are recent 2026 arXiv preprints. This axis measures citation uptake and scholarly influence, which needs more time and data.
Focus—
A focus score is not computed. OpenAlex lists 5 topics with 1 work each — formal verification, software engineering methodologies, 3D shape modeling, GAN-based image synthesis, and AI ethics — too few works to establish a concentration profile.
Collaboration63/100
The collaboration dimension scores 63/100. OpenAlex records 23 distinct co-authors in the window, with 12 frequent collaborators — among them Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Shihan Dou, and Junjie Ye — indicating dense team-based work. Both catalog papers are multi-authored: first author on the BT–FSM framework and a middle-position co-author on ExplorationBench, with no corresponding-author role on either, consistent with a contributing member of larger groups.
Activity40/100
The activity dimension scores 40/100. The OpenAlex counts-by-year series contains a single year — 2026, with 3 works — and recent3yWorks confirms 3 works over the past three years, so all recorded output is concentrated in one burst. Both reviewed papers appeared on arXiv in 2026. This is consistent with an early-stage record whose activity level cannot yet be judged across multiple years.
Reproducibility—
No aggregate reproducibility score exists yet. The only signals are Evolve's per-paper readiness labels: medium for the BT–FSM conversion framework (NuSMV-verified pipeline) and low for ExplorationBench (small samples). This axis measures artifact availability and independent replication.
Research summary
Qi Zhang is an early-stage researcher working across large language models, formal methods, and autonomous intelligent systems; this profile is name-resolved from public OpenAlex bibliographic data, with no institution or career history on record. The Evolve catalog holds two 2026 arXiv papers. The first-authored BT–FSM unified conversion framework paper converts between behavior trees and finite state machines using an LEBT representation with depth compression, verified by a NuSMV pipeline for behavioral equivalence; Evolve finds the pipeline promising but flags informal proofs and weak baselines. The middle-authored ExplorationBench measures AI systems' exploration in verifiable alien worlds with exact grading, though n=3 trajectories and single-run controls limit statistical strength. Bibliometrics are thin: OpenAlex reports h-index 0 and i10-index 0, with 3 works in the recent three-year window, all in 2026, and five topics — formal verification, software engineering methodologies, 3D shape modeling, GAN image synthesis, and AI ethics — each appearing once, so no settled focus has emerged. Collaboration is the strongest measurable signal: 23 distinct co-authors and 12 frequent collaborators yield a collaboration score of 63/100 and an activity score of 40/100. Output, impact, focus, and reproducibility cannot yet be scored from the available data.
Collaboration pattern
OpenAlex records 23 distinct co-authors in the current window, with 12 recurring collaborators — including Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Shihan Dou, and Junjie Ye — anchoring a large, team-based working pattern. Both catalog papers are multi-authored: Qi Zhang leads the BT–FSM framework as first author and sits mid-list on ExplorationBench, with no corresponding-author role on either, matching the collaboration score of 63/100.
Research keywords
Highlights
First-authored LLM-driven BT–FSM unified conversion framework
Co-authored ExplorationBench for verifiable alien-world exploration
Wide, team-based collaboration footprint
The OpenAlex snapshot lists 23 distinct co-authors and 12 frequent collaborators, including Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Shihan Dou, and Junjie Ye, alongside five single-work topics spanning formal methods to AI ethics.
Timeline
- 2026Publishes first-authored 'Towards An LLM-Driven Unified Conversion Framework for BT and FSM in Autonomous Intelligent Systems' on arXiv, with a NuSMV-verified behavioral-equivalence pipeline.
- 2026Co-authors 'ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds' (middle author position, arXiv).
- 2026OpenAlex snapshot records 3 works in the recent three-year window, all dated 2026, with h-index 0 and i10-index 0.
- 2026Collaboration network in the same snapshot spans 23 distinct co-authors, 12 of them recurring collaborators.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- 'Qi Zhang' is a very common name; this profile is resolved from public OpenAlex bibliographic data, and identity boundaries may merge or split records.
- All bibliometrics (h-index 0, i10-index 0, works counts, topics) come from a single OpenAlex snapshot; no ORCID, Scopus, or Google Scholar data was available.
- Only the 2 Evolve-reviewed papers are individually assessed; the third OpenAlex-recorded work is not in the reviewed catalog.
- Institution, country, and career history are absent from the input; output, impact, focus, and reproducibility dimensions lack sufficient data to score.