From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
Research
Research News
New papers, breakthroughs and academic AI research
Programmatic Search Agents: Extending Agentic Search Beyond Query Reformulation
Research
MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks
Research
SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor Detection
Research
Domain adaptation of Russian ModernBERT for long legal documents
Research
Improving Diversity in LLM Short Story Generation
Research
ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring
Research
What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals
Research
Physics-Augmented Graph Transformers for Patch-Antenna Forward and Inverse Design
Research
MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code
Research
ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement
Research
Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs
Research