8 papers
Context Distillation as Latent Memory Management
Ziyang Zheng, Zeju Li, Xiangyu Wen +5
Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories should be stored, retrieved,…
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…
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization
Xiaoyong Mei, Tingting Zuo, Da Chen +5
Multi-role dialogue summarization requires modeling complex interactions among multiple speakers while preserving role-specific information and factual consistency. However, most e…
FormalRTL: Verified RTL Synthesis at Scale
Kezhi Li, Min Li, Xiangyu Wen +4
Large language models (LLMs) have demonstrated significant potential in automating hardware synthesis, yet substantial barriers remain for industrial-scale, datapath-centric design…
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…
Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
Xiangyu Wen, Junhua Huang, Zeju Li +6
The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Mod…