collaborators

15 papers

cs.IR2026

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning

Zeju Li, Ziyang Zheng, Yizhou Zhou +1

Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories. Standard retrieval-…

cs.CR2026

From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers

Xiangyu Wen, Yuang Zhao, Xiaoyu Xu +9

The transition of agentic AI from brittle prototypes to production systems is stalled by a pervasive crisis of craft. We suggest that the prevailing orchestration paradigm-delegati…

cs.LG2026

DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings

Zedong Peng, Zeju Li, Qiang Xu +1

High-Level Synthesis (HLS) compiles C/C++ into RTL, but exploring pragma-driven optimization choices remains expensive because each design point requires time-consuming synthesis.…

cs.AI2026

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy

Zeju Li, Jianyuan Zhong, Ziyang Zheng +5

Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to incre…

cs.LG2026

Latent Context Compilation: Distilling Long Context into Compact Portable Memory

Zeju Li, Yizhou Zhou, Qiang Xu

Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, whic…

cs.SE2025

From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering

Qiang Xu, Xiangyu Wen, Changran Xu +2

The advent of powerful Large Language Models (LLMs) has ushered in an ``Age of the Agent,'' enabling autonomous systems to tackle complex goals. However, the transition from protot…