Xin Li李鑫

Ph.D. student · Nanyang Technological University · advised by Prof. Chau Yuen

Xin Li李鑫

I work on LLM agents — measuring what they can do, training them, and finding out what happens when several work together. Lately, on agents that improve themselves.

Portrait of Xin Li

The research, as one loopclockwise from 01

03

Coordinate

When several models work together, does the interaction help — or quietly destroy answers that were already right?

03 → 01. Coordination creates new failure modes, which have to be measured too.

So far, mostly where an answer can be checked:formal verificationmathematicscodeNow, self-improvement where it can't.

RecentAll news →

  1. Our paper SIM-D2NN (on onboard terrain classification straight from raw SAR data, using a stacked metasurface as the classifier) was accepted to IEEE Transactions on Signal Processing.
  2. Two of our papers were accepted to the NeurIPS 2026 Evaluations and Datasets Track: WirelessMathBench-XL, a wireless-math benchmark shipped with a rerunnable contamination audit, and DebateLedger, a protocol separating harmful collapse from useful correction in multi-agent LLM debate.
  3. Two of our papers were accepted to EMNLP 2026: TLVC, on picking the right verifier for best-of-K reasoning selection (Findings), and GraphReduce, on coverage-preserving LLM aggregation of e-commerce reviews (Industry Track).
  4. Our paper RobustMAD (a robustness benchmark for multimodal small language models in anomaly detection) was accepted to TMLR.
  5. Our paper Re:Form (on cutting human priors from RL-trained formal software verification) was accepted to TMLR.

Before the Ph.D.

Robot perception — visual-inertial odometry at MEGVII, RGB-D + IMU indoor mapping at Microsoft Research Asia, and multimodal localization at Gausium Robotics, where I led a five-engineer team and shipped to a fleet of 1,000+ commercial cleaning robots. More →

Contact

Always glad to talk about research or collaboration.

xin019@e.ntu.edu.sgScholarGitHubLinkedInCV