MCP Atlas
PulseAugur coverage of MCP Atlas — every cluster mentioning MCP Atlas across labs, papers, and developer communities, ranked by signal.
3 天有情绪数据
-
Google 的 Gemini 3.5 Flash 在编码和代理任务上超越 3.1 Pro
Google 的 Gemini 3.5 Flash 模型在多项关键基准测试中超越了其前身 Gemini 3.1 Pro，尤其是在编码和代理任务方面。这一新层级相比 3.1 Pro 提供了显著的成本降低 40%，并且输出生成速度大约快四倍。虽然 Gemini 3.5 Flash 在工具使用和代理性能方面表现出色，但 Gemini 3.1 Pro 在纯粹推理和新颖问题解决基准测试中仍保持优势。
-
EnvFactory automates LLM tool-use training with synthesized environments
Researchers have developed EnvFactory, an automated framework designed to enhance the tool-use capabilities of large language models through agentic reinforcement learning. This system synthesizes executable tool enviro…
-
Google DeepMind releases Gemini 3.5 Flash for faster agentic tasks
Google DeepMind has launched Gemini 3.5 Flash, a new frontier intelligence model optimized for speed and agentic tasks. This model excels at complex, long-horizon tasks in coding and agent development, outperforming pre…
-
MCP-Atlas benchmark tests LLM tool-use competency with real servers
Researchers have introduced MCP-Atlas, a new benchmark designed to evaluate the tool-use capabilities of large language models. This benchmark features 36 real MCP servers and 220 tools, with 1,000 tasks requiring multi…