AI
From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving
Researchers have developed a method for language models to solve constraint problems more reliably. ...
AI
Task-Driven Three-Layer Distributed Scheduling for Emergency Earth Observation in Large Low-Earth-Orbit Constellations
Researchers from Qian Yin and colleagues propose a task-driven three-layer distributed scheduling me...
AI
CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs
Researchers have developed a new framework called CEDAR-GRPO to improve the abductive reasoning capa...
AI
Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous
A new study explores the concept of an AI advice channel that can influence human behavior without d...
AI
Generated Context versus Governed State: Functional Conditions for Accountable Longitudinal Clinical Reasoning
Researchers argue that current large language models (LLMs) used in clinical AI ...
AI
Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking
Researchers evaluated how well large language models (LLMs) can ask questions an...
AI
MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment
Researchers have proposed a new method for training language agents to balance m...
AI
What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering
Researchers have developed a new system called Trident for answering questions a...