MP

Mugen Peng

Beijing University of Posts and Telecommunications

Unclaimed · AI-structured profileORCID OpenAlex

Satellite researcher linking LLM-driven QoS routing for LEO networks with semantic feature transmission for remote sensing

2

papers here

2

reviewed by Evolve

0

first-author

0

corresponding

—

works · OpenAlex

—

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-10-02) 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: insufficient dataOutputImpact: insufficient dataImpactFocus: 0/100FocusCollaboration: 39/100CollaborationActivity: insufficient dataActivityReproducibility: 55/100Reproducibility

Output—

No output score is available: the underlying data does not yet include total publication counts or venue breakdowns for this researcher. This axis would measure cumulative paper volume across years and across venues, distinguishing preprints from peer-reviewed publications.

Impact—

No impact score is available: citation counts, h-index, and citation-based influence metrics are absent from the current snapshot. This axis would measure how often this researcher's papers are cited by others across the bibliographic record.

Focus0/100

Focus scores 0/100, driven by the raw field distribution: the two cataloged 2026 papers split evenly (0.5/0.5) between computer networks (LEO satellite communications) and satellite remote sensing / semantic communications. Rather than concentrating on a single specialty, current work bridges two adjacent areas — networking-side LLM agents and wireless-side semantic transmission — both anchored in satellite systems. The even split signals breadth across satellite research rather than depth in one subfield.

Collaboration39/100

Collaboration scores 39/100, with 6 distinct coauthors recorded in the snapshot. Both cataloged 2026 papers list this researcher in a middle authorship position without a corresponding-author role, indicating contribution within a team rather than leading an independent group. The recurring cluster — Hongyu Wang, Wenjia Xu, Bowen Lu, Yaohua Sun, Kerui Guo, and Shuoyuan Sun — suggests a stable working group spanning both the networking and semantic communication lines.

Activity—

No activity score is available: year-by-year publication cadence cannot be computed from the current snapshot, which ties this researcher to 2026-dated records only. This axis would measure publishing consistency and recent output velocity over time.

Reproducibility55/100

Reproducibility scores 55/100, the mean across 2 assessed papers, both rated medium reproducibility readiness. For STR-Agent, reported gains (intent fulfillment 45%→92%, roughly 60% delay cut) come from synthetic evaluation with weak baselines; the semantic transmission paper shows large low-SNR gains over reconstruction JSCC, but its baselines lack task-aware training. Numbers are promising while confidence is capped by evaluation design.

Research summary

Mugen Peng is a researcher at Beijing University of Posts and Telecommunications (ORCID 0000-0002-4755-7231) working at the intersection of LEO satellite networking and semantic communications for satellite remote sensing. The Evolve catalog holds two 2026 arXiv papers, both with middle-position authorship and no corresponding role. The first, STR-Agent, presents an LLM-driven agent that converts natural-language requests into QoS-adaptive routing in LEO satellite networks; Evolve notes large reported gains — intent fulfillment rising from 45% to 92% and roughly 60% delay reduction — while flagging synthetic evaluation and weak baselines. The second proposes task-oriented semantic feature transmission for multi-task satellite remote sensing over low-SNR channels, sending frozen-backbone features through a small convolutional channel adaptation module with substantial low-SNR gains over reconstruction-based JSCC, though baselines lack task-aware training. Bibliometrically, the profile shows an even 50/50 field split between the two areas (focus 0/100), a collaboration score of 39 built on 6 distinct coauthors, and a reproducibility score of 55 averaged over 2 assessed papers, both rated medium reproducibility readiness. Output, impact, and activity scores are not yet computable from the available snapshot. This is an early-stage profile: both records are recent preprints, and conclusions about trajectory should remain provisional.

Collaboration pattern

Both cataloged 2026 papers place Mugen Peng in a middle authorship position without a corresponding role, consistent with contributing inside a team. The snapshot records 6 distinct coauthors, and the recurring cluster — Hongyu Wang, Wenjia Xu, Bowen Lu, Yaohua Sun, Kerui Guo, and Shuoyuan Sun — spans both research lines, LEO satellite networking and satellite remote sensing / semantic communications, suggesting a stable working group rather than scattered ad-hoc collaborations.

Research keywords

LLM agentLEO satellite networksQoS-aware routingintent-based networkingsupervised fine-tuningDijkstra routingtask-oriented semantic communicationjoint source-channel coding (JSCC)satellite remote sensinglow-SNR robustnessmulti-task pretrainingchannel adaptation module

Highlights

Timeline

  1. 2026Posts STR-Agent, an LLM-driven agent for QoS-aware routing in LEO satellite networks, to arXiv as a middle-position author.
  2. 2026Publishes task-oriented semantic feature transmission for multi-task satellite remote sensing over low-SNR channels on arXiv, again in a middle authorship position.
  3. 2026Both cataloged works land in the same year, splitting output evenly between LEO satellite networking and satellite remote sensing / semantic communications.

Papers in the Evolve catalog

Frequent co-authors

Is this you? Claim this profile

Enter the email you published with. We'll send a one-time claim link; after claiming you can edit the introduction or hide this page. Requests from a mismatched address go to manual review.

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.

  • Bibliometric scores (collaboration, focus, reproducibility) are computed from Evolve's OpenAlex-based snapshot only.
  • Output, impact, and activity scores are unavailable — no publication counts, citation metrics, or multi-year cadence data are in scope.
  • Both cataloged papers are 2026 arXiv preprints; peer-review status and final venues are not reflected.
  • Records are name-resolved from public bibliographic data via ORCID 0000-0002-4755-7231; country is not recorded in the source data.
Mugen Peng — Researcher Profile | Evolve.Pub