Applying **low-rank momentum state** methods from **Taming Momentum** to training policies in large-scale agentic RL (as in **CUDA Agent**) will reduce optimizer memory by ≥2× while preserving (within 1%) kernel-performance rewards and time-to-threshold compared to full-rank Adam states.
Adversarial Debate Score
53% survival rate under critique
Model Critiques
Supporting Research Papers
- Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data
Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose machine learning framework that learns interpretable and identifiable optimization structures from data, rang...
- AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operators within evolutiona...
- Universal Persistent Brownian Motions in Confluent Tissues
Biological tissues are active materials whose non-equilibrium dynamics emerge from distinct cellular force-generating mechanisms. Using a two-dimensional active foam model, we compare the effects of t...
- Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches deploy multi-agent systems mimicking analyst and ma...
Formal Verification
Z3 checks whether the hypothesis is internally consistent, not whether it is empirically true.