Early-stage researcher in LLM-based UAV swarm coordination; first author of the AeroWeaver embodied-agent harness
1
papers here
1
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-21) 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—
This axis would measure publication volume, venue types, and authorship roles over time. The current snapshot contains only one reviewed paper, so no output score can be computed honestly; the axis remains unscored until a fuller bibliographic record is ingested.
Impact—
This axis would measure citation uptake and downstream influence of the researcher's work. No citation counts or influence metrics exist in this snapshot, so impact cannot be scored honestly; it stays unscored until citation data becomes available.
Focus100/100
The focus score of 100 is derived from a field distribution containing exactly one field — robotics / multi-agent AI (LLM-based UAV swarms) — accounting for the full catalogued output. This signals complete topical concentration, but on a sample of one paper; it should read as perfectly focused so far, not yet as a demonstrated long-term single-field program.
Collaboration44/100
The collaboration score of 44 comes from 8 distinct coauthors recorded on the catalogued work — Yirong Yang, Haopeng Wang, Xuxin Lv, Xinyu Liu, Diyuan Hou, Xuehong Liu, Rongye Shi, and Wenjun Wu — with Jiabin Lou in the first-author position. The team is compact and internally consistent, suggesting one core group; with only one paper in the sample, the score describes this single collaboration footprint rather than an established network.
Activity—
This axis would measure recent publishing cadence, such as outputs per year and recency of contributions. Only a single 2026 arXiv entry is present, so sustained activity cannot be assessed; the axis is left unscored rather than estimated from one data point.
Reproducibility55/100
The reproducibility score of 55 is the mean over exactly one assessed paper (reproPapers = 1): AeroWeaver, whose Evolve review credits consistent simulated gains while flagging thin baselines and limited statistics, and whose repro readiness is rated medium. It indicates a workable but not frictionless replication path; a single-paper mean should be treated as a preliminary signal only.
Research summary
Jiabin Lou is an early-stage researcher working at the intersection of large language models and multi-robot systems, with the catalogued record centered on LLM-based UAV swarm coordination. The profile rests on one reviewed paper, AeroWeaver (arXiv, 2026), a first-authored embodied-agent harness that weaves reusable aerial skills into distributed, adaptive swarm execution: decentralized LLM agents coordinate the swarm, skills are grounded for execution, and a training-free reward memory enables experience reuse across tasks. Evolve's review credits the system with consistent simulated gains while flagging thin baselines and limited statistical treatment — a fair reading of a promising but early result. Bibliometric signals are correspondingly narrow. The focus score of 100 reflects a record concentrated in a single field; the collaboration score of 44 reflects eight distinct coauthors; the reproducibility score of 55 is the mean over one assessed paper rated at medium readiness. Output, impact, and activity axes cannot be scored from this snapshot. The co-author cluster — Yirong Yang, Haopeng Wang, Xuxin Lv, Xinyu Liu, Diyuan Hou, Xuehong Liu, Rongye Shi, and Wenjun Wu — is compact, consistent with one core team rather than a wide network. With institution, country, and ORCID unverified, this is a name-resolved profile: directionally useful, but built on a thin evidentiary base.
Collaboration pattern
All catalogued evidence comes from one first-authored paper with eight distinct coauthors — Yirong Yang, Haopeng Wang, Xuxin Lv, Xinyu Liu, Diyuan Hou, Xuehong Liu, Rongye Shi, and Wenjun Wu — yielding a collaboration score of 44. The pattern is consistent with a single close-knit team rather than repeated external partnerships. With one paper in the sample, the score describes this footprint only and may shift as more work is indexed.
Research keywords
Highlights
First-authored AeroWeaver harness for UAV swarms
Training-free reward memory for experience reuse
Consistent simulated gains, thin baselines
Timeline
- 2026Posts AeroWeaver to arXiv as first author — an embodied-agent harness weaving aerial skills into distributed, adaptive swarm execution for LLM-based UAV swarms.
- 2026The paper enters the Evolve catalog; the review notes consistent simulated gains alongside thin baselines and limited statistics.
- 2026Bibliometric snapshot recorded: eight distinct coauthors, a single-field record (focus 100), and a reproducibility mean of 55 from one assessed paper.
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.
- Profile is name-resolved from public bibliographic data; 'Jiabin Lou' is not disambiguated by ORCID or a verified affiliation.
- All scores rest on a very small sample — one reviewed paper and eight distinct coauthors; focus = 100 reflects a single-field record, not demonstrated breadth.
- Output, impact, and activity dimensions lack underlying data (no publication counts or citations in this snapshot) and are intentionally left unscored.
- Institution, country, and ORCID are absent; no career facts beyond the 2026 arXiv entry are asserted.