7 papers
When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents
Yanjie Zhang, Bowen Cao, Zixin Chen +1
LLM agents often operate over multi-turn interactions in which user intent changes before execution. We study intent drift: the failure mode in which superseded parts of the user's…
EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language Rendering
Ziliang Zhao, Zenan Xu, Shuting Wang +6
In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier information, changing what remains va…
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…
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…
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
Yushi Sun, Bowen Cao, Dong Fang +2
Long-horizon memory systems increasingly improve how evidence is stored and retrieved, yet the generator must still reason over fragments whose cross-session relationships are impl…
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…
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.…