16 papers
ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling
Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +5
Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sust…
RaMem: Contextual Reinstatement for Long-term Agentic Memory
Wei Yang, Bryce Kan, Shixuan Li +5
Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experie…
COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation
Heng Ping, Peiyu Zhang, Shixuan Li +5
LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet existing approaches universally decouple the two objectives, optimizing P…
VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation
Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +8
Automation of Register Transfer Level (RTL) design can help developers meet increasing computational demands. Large Language Models (LLMs) show promise for Hardware Description Lan…
ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
Anzhe Cheng, Shukai Duan, Shixuan Li +8
Mixture-of-Experts (MoE) architectures expand model capacity by sparsely activating experts but face two core challenges: misalignment between router logits and each expert's inter…
POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
Heng Ping, Peiyu Zhang, Zhenkun Wang +5
Applying large language models (LLMs) to RTL code optimization for improved power, performance, and area (PPA) faces two key challenges: ensuring functional correctness of optimize…