14 posts published in the last hour
- 10:33Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
- 10:33GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG
- 10:33AI’s recursive self-improvement might not come so quickly after all
- 10:33TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning
- 10:33Claude Code gets a /design command that lets developers create UI mockups right in the terminal
- 10:33Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning
- 10:32We still don’t know how people are really using AI
- 10:32LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents
- 10:03S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices
- 10:03LLM-Based Hierarchical Coordinated Control with Continuation-Aware Policy Learning
- 10:03SCOPE: Score-Isolated Agentic Optimization for Video World Models
- 10:03Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form
- 10:03Reading Zhipu’s GLM-5.3 results past the headline number
- 10:03Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research
