MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games
Research
Research News
New papers, breakthroughs and academic AI research
What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality
Research
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
Research
ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training
Research
ScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents
Research
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
Research
"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It
Research
Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow
Research
The MODA General Attribute Suite: A Four-Track Evaluation Benchmark for Fashion Attribute Extraction
Research
Exposing Blind Spots in Deep Imbalanced Regression Evaluation
Research
AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search
Research
DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models
Research