Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
Research
Research News
New papers, breakthroughs and academic AI research
LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search
Research
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
Research
Beyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts
Research
A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies
Research
CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation
Research
From Scientific Observations to Mechanisms: Benchmarking Hypothesis Generation by AI Scientists
Research
Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
Research
Geometry-Aware Preference Optimization for Text-to-Image Diffusion Models
Research
PortraitAes: Intent-Conditioned Structured Portrait Aesthetics Assessment
Research
AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems
Research
Revisiting the Generalization of Neural Graph Edit Distance Models
Research