collaborators

5 papers

cs.DB2026

When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers

Yushi Sun, Bowen Cao, Wai Lam

LLM agents increasingly rely on retrieval buffers to store and reuse past experience, yet the cache management policies governing these buffers remain largely ad-hoc. We formalize…

cs.LG2026

Looped World Models

Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28

Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding error…

cs.DB2026

APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL

Bowen Cao, Weibin Liao, Yushi Sun +3

Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments. The primary limitation lies in their reli…

cs.CL2026

GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory

Yushi Sun, Bowen Cao, Dong Fang +2

Long-horizon conversational agents rely on memory systems with increasingly sophisticated retrieval mechanisms. However, retrieved fragments are typically fed to the language model…

cs.AI2026

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics

Bowen Cao, Dongdong Zhang, Yixia Li +8

Large language models now solve many benchmark math problems at near-expert levels, yet this progress has not fully translated into reliable performance in real-world applications.…