AI researcher bridging multi-agent LLM writing systems and heuristic search; last author on two 2026 arXiv papers
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) 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—
Not yet scored: the bibliometric snapshot lacks publication counts and yearly output totals. This axis would measure the volume and regularity of papers across venues and years; no estimate is offered until those counts are available.
Impact—
Not yet scored: no citation counts, h-index, or per-paper citation data are present in the snapshot. This axis would measure citations, influence, and uptake of the two reviewed 2026 papers; no impact estimate is made.
Focus0/100
Scores 0/100, the lowest focus reading, driven by an exactly even field distribution: 0.5 weight in natural language processing for scientific text generation and 0.5 in heuristic search / artificial intelligence. The two cataloged 2026 papers sit one in each area, so the record currently reads as two-track rather than concentrated; more papers in either line would sharpen this picture.
Collaboration46/100
Scores 46/100, a moderate level, with 9 distinct coauthors recorded in the bibliometric snapshot. The nine recurring names include Hai-Dang Dang, Bao-Yen Pham, Bao Nguyen, Tran Thi Huong, Minh Vu Duc, Trung Le Huu, Hà Minh Hoàng, Trung Thanh Nguyen, and Phuong Khanh Nguyen, indicating a stable working group rather than wide external networking; on both cataloged 2026 papers she appears in the last author position, a slot often associated with senior roles.
Activity—
Not yet scored: the snapshot contains no multi-year publication timeline beyond two 2026 catalog entries, so publishing cadence cannot be computed. This axis would measure annual output and consistency over time; it stays unscored until earlier-year records are available.
Reproducibility78/100
Scores 78/100, computed as a mean of 78 across the 2 papers Evolve has reviewed. The split is uneven: Probabilistic Focal Search is rated high reproducibility readiness, supported by a sound w-bound proof and concrete N-Puzzle/TSP experiments, while CREW sits at medium, its +0.06 quality margin and missing significance tests tempering confidence. Overall this is the strongest quantitative signal in the profile.
Research summary
Huynh Thi Thanh Binh (ORCID 0000-0003-1976-6113) is profiled here from public bibliographic data and two Evolve-reviewed papers, both posted to arXiv in 2026 with her listed as last author (non-corresponding). Her cataloged work splits evenly — 0.5 and 0.5 — between natural language processing for scientific text generation and heuristic search in artificial intelligence, which drives the focus score of 0. The first paper, 'Assembling the CREW', trains LLM agents with IPPO under a Dec-POMDP formulation to coordinate related-work writing; Evolve's verdict notes strong citation gains but marginal quality improvement (+0.06), no significance tests, and medium reproducibility readiness. The second, 'Probabilistic Focal Search', combines FOCAL guidance with min-f expansions through a Bernoulli draw and carries a sound w-bound proof, with large N-Puzzle/TSP gains despite thin baselines and statistics; it rates high for reproducibility readiness. These reviews average to a reproducibility score of 78/100 over 2 papers — the profile's strongest metric. Collaboration scores 46/100 on 9 distinct coauthors, suggesting a compact working group. Output, impact, and activity metrics are missing, and no institution or country is recorded.
Collaboration pattern
The record shows 9 distinct coauthors and a moderate collaboration score of 46/100, pointing to a stable, compact working group rather than an extensive international network. Recurring partners include Hai-Dang Dang, Bao-Yen Pham, Bao Nguyen, Tran Thi Huong, Minh Vu Duc, Trung Le Huu, Hà Minh Hoàng, Trung Thanh Nguyen, and Phuong Khanh Nguyen. On both 2026 papers she occupies the last author position without corresponding-author status, a pattern often associated with a senior team member guiding junior first authors.
Research keywords
Highlights
CREW: multi-agent reinforcement learning for automated related-work generation
Probabilistic Focal Search: bounded-suboptimal search with lower-bound advancement
Timeline
- 2026arXiv posting of 'Probabilistic Focal Search', introducing Bernoulli-mixed FOCAL/min-f expansions with a sound w-bound proof for bounded-suboptimal search (last author; Evolve rates reproducibility readiness high).
- 2026arXiv posting of 'Assembling the CREW', an IPPO-trained multi-agent LLM framework for automated related-work generation (last author; Evolve rates reproducibility readiness medium).
- 2026Both 2026 papers entered the Evolve review catalog, giving an even 0.5/0.5 split between scientific text generation and heuristic search and a mean reproducibility score of 78 across 2 reviewed papers.
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.
- Radar scores are computed from a bibliometric snapshot only; the output, impact, and activity axes are missing and therefore unscored.
- Only 2 papers (both 2026, arXiv) are in the reviewed catalog, so the profile rests on a very small sample.
- Institution, country, and career history are absent from the source data; the profile is name-resolved from public bibliographic data via ORCID 0000-0003-1976-6113, with no further disambiguation performed.
- Field distribution and author-position facts describe only the two reviewed papers, not the researcher's full publication record.