AI
SCOPE: Score-Isolated Agentic Optimization for Video World Models
Researchers have developed a framework called SCOPE for improving video world models used in planning and decision-making. These models are simulators...
AI
AI
Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research
Researchers have developed an AI system called Andy that can assist with mathematical research by solving and verifying problems, formulating new rese...
AI
TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning
Researchers have introduced TAHB (Text-Attributed Hypergraph Benchmark), a comprehensive benchmark for text-attributed hypergraph learning. The benchm...
AI
GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG
GraphLoom is a new framework for multimodal knowledge-graph retrieval-augmented generation (RAG) systems. It aims to improve the reliability and faith...
AI
LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents
Researchers have created a new benchmark called LongDocBench to evaluate the ability of AI systems to understand and reconstruct the structure of long...
AI
Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning
Researchers have developed a method called Funnel of Thoughts (FoT) to improve the efficiency of large reasoning models. These models often produce in...
AI
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
Researchers have developed a method called Evo-Harness that allows self-improving large language model agents to learn from experience in complex real...
AI
Beyond Thresholds: A Quality-Aware Decision Intelligence Framework for Cold Chain IoT Systems
Researchers have developed a decision-making framework for IoT systems in cold chain logistics that goes beyond simple threshold monitoring. The Quali...
AI
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling
Researchers have developed a new agent-native runtime called StateM that improves the execution system around an existing AI model without changing it...
AI
Validation-Frontier Representation Selection under Constrained Observation
Researchers propose a new method for choosing the best state representation when observations are incomplete or unreliable. The approach balances accu...
AI
Second-Order Policy Effects as State Transitions: A Source-Linked Benchmark for Policy Simulation
Researchers have developed a new benchmark for evaluating how policies affect complex systems over time. Their method, called second-order policy-effe...
AI
Constraint-Aware Synthetic Tabular Data Generation via Inter-Column Constraint Discovery with LLM Agents
Researchers have developed a method to generate synthetic tabular data that adheres to domain-specific constraints. The approach involves discovering ...