Teaching Agents to Code Reliably
Research
Research News
New papers, breakthroughs and academic AI research
SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
Research
Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models
Research
REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers
Research
Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities
Research
Exploration-Preserving Policy Optimization
Research
DABACO: A Multi-Camera Dataset and Benchmark for Screen Localization and Pointing Estimation
Research
Periscope: Extending Frozen Language Models Beyond Their Context Window
Research
Dynamic Time Step Prediction in Inverse Heat Dissipation for Blur-Like Image Restoration Tasks
Research
IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation
Research
FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning
Research
From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model Agents
Research