7 papers
CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation
Hejia Zhang, Sheng Lu, Zhongming Yu +3
Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation alone. Hardware verification i…
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
Zhongming Yu, Hengjia Yu, Boqin Yuan +12
Coding agents repeatedly search, navigate, and retain context from evolving repositories, but disconnected indexes, language servers, and task-local histories force repeated discov…
LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation
Hejia Zhang, Zhongming Yu, Chia-Tung Ho +3
Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback can be expensive and slow to obtain, making online reinforcement learning (…
AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
Yujie Zhao, Boqin Yuan, Junbo Huang +9
Large Language Models (LLMs) are increasingly used as autonomous agents in complex, long-horizon applications, where effective memory is critical for sustained performance. Yet exi…
Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead
Zhongming Yu, Naicheng Yu, Hejia Zhang +5
As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer archi…
Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs
Wentao Ni, Kangqi Zhang, Zhongming Yu +7
As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse atte…