AI News
업데이트:
Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive self-improvement (RSI). Workflow-driven machine learning engineering (MLE)
Selected for strong relevance to: agent, ai, llm.
https://x.com/Jiaru_Zou/status/2110400256647340476 https://github.com/togethercomputer/HybridAgent https://huggingface.co/collections/togethercomputer/hybridag... Evaluations: https://arxiv.org/html/2610.18861v1#S5
Selected for strong relevance to: agent, agents, llm.
Autonomous AI agents fail softly: latency stays flat while answer quality quietly erodes. This post shares a nine-stage evaluation framework, built on Amazon Bedrock AgentCore, that catches silent quality regressions across the full agent lifecycle, from first commit to live prod
Selected for strong relevance to: agent, agents, ai.
We’re launching ReviewBench, a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics. The post ReviewBench: An open benchmark for AI code review appeared first on The GitHub
Selected for strong relevance to: agent, agents, ai.
General Science
Selected for strong relevance to: agent, agents, ai.
One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of this work optimizes the quality of individual ideas, while overlooking diversity. In our work, we study document-grounded ideat
Selected for strong relevance to: ai, llm, large language model.
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is different: forward-deployed engineers (FDEs) must clarify ambiguous requirements, work in live systems, and uncov
Selected for strong relevance to: agent, agents, ai.
Reflection AI's Beam is an open-weight model for agentic coding and long-horizon tasks. This post shows how to deploy Beam on AWS: start with an Amazon SageMaker JumpStart real-time endpoint, or use Amazon SageMaker HyperPod Inference with JumpStart, SGLang, or vLLM for Kubernete
Selected for strong relevance to: agent, ai, llm.
We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality datasets of executable 3D code, a coding harness for spatial reasoning and automated verification, and
Selected for strong relevance to: agent, agents, reasoning.
Large language models (LLMs) can often tell when they are being tested. This ability, known as evaluation awareness, can lead models to act more cautiously during safety evaluations than in real use. Existing work has studied evaluation awareness almost entirely in English, altho
Selected for strong relevance to: llm, large language model, evaluation.
Continuous diffusion language models (CDLMs) offer an alternative approach to parallel language generation; however, most existing studies directly use transformer architectures from either causal large language models (LLMs) or Diffusion Transformers (DiTs) for image generation,
Selected for strong relevance to: llm, large language model, transformer.
AI, agents, voice, and physical controls are shifting software development from operating tools to expressing intent—and helping developers stay focused on building. The post The next developer interface is ambient intelligence appeared first on The GitHub Blog . ]]>
Selected for strong relevance to: agent, agents, ai.
