12 posts published in the last hour
- 10:35SERIAL-7: Deriving, Realizing, and Preserving Machine-Verifiable Outputs Across Representations
- 10:35SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences
- 10:35Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer
- 10:35Subliminal Reinforcement Learning: traits travel through a judge’s scores
- 10:34Why AI Agents Need Evidence Before They Retry
- 10:34Operon-S1: a fast decision controller for long-horizon biomedical agents
- 10:06From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation?
- 10:06Experts Exhibit Structured Redundancy: Structure-Preserving Expert Pruning for Mixture-of-Experts Large Language Models
- 10:06SciGraphSelect: Auditable Scientific Data Selection through Knowledge–Reasoning Graphs
- 10:05MEMIG: Self-evolving Memory Construction for Antibody Optimization
- 10:05The agentic web is here
- 10:05Rome Wasn’t Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents