Skip to content

Author

Yuanda Xu

We have 6 of 20 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

A sharp lower bound for the sextic large sieve

We establish a matching lower bound for the sextic large sieve over the Eisenstein integers in an unbalanced range, with both indices restricted to squarefree ideals. Let $\Xi_6(A,B)$ denote the squared operator norm of the sextic residue-character matrix with row and column norms at most $A$ and $B$, respectively, out...

Yuanda Xu, He-Jian Sang · 0 citations
#artificial intelligence Preprint Oct 2026

Budgeted KV-Cache Repair for Evolving Contexts

Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation. Later key-value (KV) states remain conditioned on the deleted content, while recomputing the entire retained suffix can be costly. We introduce budgeted KV-cache repa...

Han Yu, Wen-Hui Zhu, Jincheng Cao et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Hierarchical Reinforcement Learning with Stable Temporal Abstraction for Language Model Agents

Hierarchical reinforcement learning improves long-horizon control by organizing primitive actions around persistent subgoals and assigning credit at multiple temporal scales. Recent hierarchical language agents bring these benefits to interactive tasks by explicitly separating subgoal planning from action execution. We...

Shayan Mohajer Hamidi, Yize Cheng, Yuanda Xu et al. · 0 citations
Review Aug 2026

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

MatrAIx is introduced, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users and provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users.

Xiaomin Li, Yuexing Hao, Jian Hou et al. · 1 citation
Jul 2026

TREK: Distill to Explore, Reinforce to Refine

TREK (Teacher-Routed Exploration via Forward KL), a simple staged procedure that uses distillation not for imitation but for exploration support expansion, achieves high success rates early in training while unaided GRPO requires substantially more optimization steps to reach comparable levels.

Yuanda Xu, Zhengze Zhou, Kayhan Behdin et al. · 0 citations
Preprint Aug 2026

CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories

Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and verifier-sensitive writes, yet they remain prone to procedural failures: misreading application state, tool semantics, or task progress. Procedural memory promises more c...

Zheyuan Deng, Bing-Hang Lu, Han-Qi Feng et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.