ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World Models
Research
Research News
New papers, breakthroughs and academic AI research
What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives
Research
Online Verification of Language Model Responses Under Cost Constraints
Research
Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective
Research
JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs
Research
Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories
Research
Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMs
Research
Optimal Planning in a Dynamic World
Research
Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers
Research
Quantifying the Value of Constructive Induction, Knowledge, and Noise Filtering on Inductive Learning
Research
KV$^2$: A Self-Refining KV Cache
Research
Toward SLM-based agentic task-tool intent matching
Research