Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition
Research
Research News
New papers, breakthroughs and academic AI research
Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games
Research
Workerville: Towards an Organizational Behavior Account of Agent Safety
Research
AgentEvolver: System-Wide Self-Evolution Through Task Execution
Research
Where to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention
Research
Harness Evolution Hits a Ceiling: When Weight Training Should Begin
Research
Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards
Research
Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper
Research
Learning the Loop, Not Just the Page: Execution-Grounded Loop Learning for Web Generation
Research
Incremental Open-Ended Deep Research with Structured Harness
Research
AutoAdapt: Reliable Few-Shot Adaptation under Clinical Distribution Shifts
Research
VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding
Research