How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws
Research
Research News
New papers, breakthroughs and academic AI research
AgentPersonaBench: Benchmarking Persona-Driven User Simulation
Research
Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation
Research
You May Be Running the Wrong Inception Crop
Research
Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents
Research
MERCI Cards: An LLM Evaluation and Deployment Framework for High-Stakes Domains
Research
Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition
Research
Physics is the Best Teacher: Consistency Learning for Time-Invariant Operators of Chaotic Dynamics
Research
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
Research
Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization
Research
CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies
Research
Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures
Research