9 papers
Software World Models: From Consequence Prediction to Decision Value
Tongli Su, Yuntong Hu, Liang Zhao +3
A coding agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it. Exhaustively running integration tests afte…
StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents
Ziyang Yu, Liang Zhao, Bowen Zhu +1
Despite the recent success of coding agents built on large language models, it remains challenging to run them over long horizons, since every observation is appended to the contex…
MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data
Xinyuan Song, Bowen Zhu, Hasibul Haque +1
Enterprise repositories are large, heteroge- neous, and continuously updated, making re- trieval difficult when efficient access, source- faithful evidence, and cross-query adaptat…
MegaMem: A Retrieval Solution for Ultra-Large Context Windows
Xinyuan Song, Bowen Zhu, Hasibul Haque +1
Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterprise records. The key challenge…
LARGER: Lexically Anchored Repository Graph Exploration and Retrieval
Yuntong Hu, Tongli Su, Liang Zhao +2
Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream objectives ranging from patch gene…
SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
Yongliang Miao, Ziyang Yu, Liang Zhao +2
Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution…
Efficient Symbolic Computation via Hash Consing
Bowen Zhu, Aayush Sabharwal, Songchen Tan +3
Symbolic computation systems suffer from memory inefficiencies due to redundant storage of structurally identical subexpressions, commonly known as expression swell, which degrades…
Multimodal Representation Learning Conditioned on Semantic Relations
Yang Qiao, Yuntong Hu, Bowen Zhu +2
Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by aligning paired image-text samples. While eff…
On a perturbation analysis of Higham squared maximum Gaussian elimination growth matrices
Alan Edelman, John Urschel, Bowen Zhu
Gaussian elimination is the most popular technique for solving a dense linear system. Large errors in this procedure can occur in floating point arithmetic when the matrix's growth…