Author

Sisong Bei

Observed name: Bei, Sisong

Institutions: Amazon (United States), Palo Alto Networks (United States)

Observed institutions: Amazon (United States), Palo Alto Networks (United States)

ORCID: 0009-0008-8379-8535

Observed ORCID: 0009-0008-8379-8535

OpenAlex ID: A5120050517

Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline

2026 · Xu, Jiawei, Koesdwiady, Arief, et al. · arXiv (Cornell University) · 1

PDF

Contextual Credit Policy Optimization

2026 · Han, Huiwen, Zeng, Ziyao, et al. · arXiv (Cornell University)

PDF

Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale

2026 · Arbuzov, Mikhail L., Dave, Karan, et al. · arXiv (Cornell University)

PDF

OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies

2026 · Wang, Mingjia, Lu, Taiting, et al. · arXiv (Cornell University)

PDF

OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D Reconstruction

2026 · Lu, Taiting, Liu, Runze, et al. · arXiv (Cornell University)

PDF

OmniRouting: A Semantic-Coupled Multimodal Benchmark for Constraint-Aware Spatial Reasoning in PCB Routing

2026 · Lu, Taiting, Lin, Kaiyuan, et al. · arXiv (Cornell University)

PDF

Context Compression Is Not One Thing: Readable Symbolic Re-expression vs. Coherent Summary at Matched Budget

2026 · Bei, Sisong, Arbuzov, Mikhail L., et al. · arXiv (Cornell University)

PDF

The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability

2026 · Arbuzov, Mikhail L., Mosbacker, Lee, et al. · arXiv (Cornell University)

PDF

Estimated Dynamic Equilibrium Model: Supply and Demand as a Sample Path of a Stochastic Process

2026 · Arbuzov, Mikhail L., Bei, Sisong, et al. · arXiv (Cornell University)

PDF

Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting

2026 · Arbuzov, Mikhail L., Bei, Sisong, et al. · arXiv (Cornell University)

PDF

RAC: Rectified Flow Auto Coder

2026 · Fang, Sen, Feng, Yalin, et al. · arXiv (Cornell University)

PDF

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data

2026 · Yuxuan Lu, Jing Huang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

PDF

Tiny Translators: pre-registered test of compression × reasoning-depth interaction in multi-hop QA (paper-3 pre-registration)

2026 · Bei, Sisong

Works count: 13

Citation count: 1

H-index: 1

I10-index: