ZL
Zhuoyun Li
cs.AIcs.CLcs.MAcs.CVcs.LGcs.RO
On Valency
published · living versionsW_juer8c7q·v1 · currentpublished
Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems
with Boxuan Wang, Jinwei Hu, Xiaowei Huang, Yi Dong
1 version
W_bj8dmwe5·v1published
Preprints & journals
10 papers in the corpus · 2025–2026SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services2606.21255v2 · Zhuoyun Li, Boxuan Wang, Changshun Wu et al.2026 · 0 citationsarXiv
ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs2606.05858v1 · Ailiang Lin, Zhuoyun Li, Yusong Wang et al.2026 · 0 citationsarXiv
Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts2606.01441v1 · Boxuan Wang, Zhuoyun Li, Xiaowei Huang et al.2026 · 0 citationsarXiv
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation2605.14174v2 · Qisong He, Xinmiao Huang, Jinwei Hu et al.2026 · 0 citationsarXiv
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness2605.08896v2 · Zhuoyun Li, Boxuan Wang, Jinwei Hu et al.2026 · 0 citationsarXiv
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models2605.01605v1 · Zhuoyun Li, Boxuan Wang, Jinwei Hu et al.2026 · 0 citationsarXiv
Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks2512.18094v1 · Boxuan Wang, Zhuoyun Li, Xiaowei Huang et al.2025 · 1 citationarXiv
Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models2510.13394v4 · Xinmiao Huang, Qisong He, Zhenglin Huang et al.2025 · 0 citationsarXiv
Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment2510.14008v2 · Jinwei Hu, Yi Dong, Shuang Ao et al.2025 · 0 citationsarXiv
Position: Towards a Responsible LLM-empowered Multi-Agent Systems2502.01714v1 · Jinwei Hu, Yi Dong, Shuang Ao et al.2025 · 2 citationsarXiv
Career total: 15 works. 10 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.