- AI · arxiv/cs.LG · 8 min
Mixed Precision Training Stabilizes Neural ODEs
Researchers demonstrate a framework that reduces memory use by 50% and speeds up neural ODE training 2x by carefully mixing low and high precision arithmetic.
May 3, 2026 Read → → - AI · arxiv/cs.AI · 8 min
Safe Bilevel Delegation: Runtime Safety Control for Multi-Agent LLM Systems
A formal framework that dynamically adjusts safety-efficiency trade-offs when delegating tasks to specialized AI sub-agents during execution.
May 2, 2026 Read → → - AI · arxiv/cs.AI · 3 min
Multi-agent framework automates recommendation system tuning
AgenticRecTune uses specialized LLM agents to optimize configuration across pre-ranking, ranking, and re-ranking pipelines without manual tuning.
May 1, 2026 Read → → - Engineering · arxiv/cs.LG · 4 min
Graph Neural Networks Cut QAOA Query Cost by 87%
A trust-region method using GNNs to predict QAOA parameter distributions reduces circuit evaluations while preserving solution quality on small graphs.
April 29, 2026 Read → → - AI · arxiv/cs.AI · 8 min
Testing POMDP Policies Against Sensor Drift and Model Mismatch
New framework quantifies how much observation noise a decision policy can tolerate before performance collapses, with polynomial-time algorithms for real systems.
April 26, 2026 Read → → - AI · arxiv/cs.AI · 8 min
GEM activation functions match ReLU speed with smoother gradients
Krause proposes rational activation functions with tunable smoothness that reduce optimization friction in deep networks while maintaining computational efficiency.
April 24, 2026 Read → → - Engineering · arxiv/cs.LG · 8 min
Multi-Agent Edge Systems Hit a Scaling Wall at 100+ Agents
A new framework addresses the Synergistic Collapse problem where performance degrades superlinearly as distributed agents grow, combining neural caching, action pruning, and hardware matching.
April 23, 2026 Read → → - AI · arxiv/cs.AI · 8 min
Q-Value Iteration Finds Optimal Actions Faster Than Theory Predicts
Lee's switching system analysis reveals Q-VI reaches practical optimality in finite time, with convergence rates potentially faster than the classical discount factor bound.
April 22, 2026 Read → → - Engineering · arxiv/cs.LG · 8 min
Routing Optimization for Satellite Federated Learning: Tractable Boundaries
Researchers map which routing problems in orbital federated learning can be solved efficiently and which are computationally hard.
April 22, 2026 Read → → - AI · arxiv/cs.LG · 8 min
Simpler Optimizers Make LLM Unlearning More Robust
Research shows that using lower-order optimization methods during LLM unlearning produces forgetting that resists post-training attacks better than sophisticated gradient-based approaches.
April 21, 2026 Read → → - AI · arxiv/cs.LG · 4 min
LLMs complement but don't replace classical hyperparameter optimization
A study comparing LLM agents to classical algorithms like CMA-ES and TPE finds hybrid approaches work best for tuning model hyperparameters under compute constraints.
April 21, 2026 Read → → - AI · arxiv/cs.LG · 8 min
Chromatic Clustering Requires New Algorithms to Match Standard Performance
Adding color constraints to correlation clustering increases computational difficulty; a new coupled approach recovers optimal approximation bounds.
April 20, 2026 Read → → - AI · arxiv/cs.AI · 4 min
AlphaCNOT: Planning-Based RL Cuts Quantum Gate Count by 32%
Researchers combine Monte Carlo Tree Search with reinforcement learning to minimize CNOT gates in quantum circuits, outperforming classical heuristics.
April 18, 2026 Read → → - AI · arxiv/cs.AI · 8 min
Automating Feature Preprocessing Beats Manual Tuning for Tabular ML
Study of 15 search algorithms on 45 datasets reveals evolution and random search outperform complex surrogate models for automated feature pipeline construction.
April 17, 2026 Read → → - AI · arxiv/cs.LG · 8 min
Action Aliasing Breaks Safe RL Differently Depending on Filter Placement
A formal comparison of two projection-based safety strategies reveals that embedding safeguards in the policy creates gradient rank deficiency, while environment-level filters distribute the problem to the critic.
April 17, 2026 Read → →