4 papers
Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
Julia Hu, Alfred Shen, Kumar Lakshmipathi
When should a language model answer directly, sample and vote, or engage in multi-agent debate? Recent work shows voting often explains much of the gain attributed to debate, while…
STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems
Alfred Shen, Aaron Shen
Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse inter…
DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation
Aaron Shen, Alfred Shen
Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation, yet single-agent systems exhibit fundamental limitations wh…
Gated Sparse Attention: Combining Computational Efficiency with Training Stability for Long-Context Language Models
Alfred Shen, Aaron Shen
The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by att…