Agent Harness Awareness: Turning Verified Telemetry into Operational Control for Tool-Using Agents
Research
Research News
New papers, breakthroughs and academic AI research
Challenge-Aware Knowledge Recruitment with Meta-Agent Supervision for Medical Multi-Agent Reasoning
Research
A Feasibility Condition for Confidence-Gated Tiered LLM Inference
Research
Towards Robust Long-Lived Agents: Benchmarking Experience Lifecycles in Evolving Environments
Research
SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories
Research
Hybrid Spark: Adaptive Speculative Decoding That Lets the Content Choose the Drafter
Research
Can Large Language Models Review the Scientific Literature? A Test Against a 102-Article Benchmark
Research
BrainBind: Bridging Synchronized EEG and fMRI through Long-Form Naturalistic Video Representations
Research
When Does Sharing Work? Scaling a Shared SigLIP2 Across Image, Video, Audio, and Audio-Visual Representations
Research
Towards Efficient Whole Page Ranking with One-Pass Inference
Research
VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
Research
Iterated creation, grading, and revision of data science projects by language models
Research