与「LatentReasoning」相关的搜索结果

Excited to share that #LatentMAS# has been accepted to ICML 2026 as a spotlight! 💻Code: 📄Paper: We push multi-agent collaboration into the latent space — beyond human language. Most multi-agent systems rely on text: agents reason in words, exchange messages, and repeatedly decode/re-encode information. But language can be slow, lossy, and unnecessarily constrained. 💡LatentMAS takes a different path: LLM agents reason and communicate directly through hidden embeddings. No text decoding. No extra training. No token-level message passing. Instead, agents collaborate through: 🧠 Autoregressive Latent Thoughts — hidden-state-level reasoning steps 🔁 Latent Communication — information sharing via KV-cache transfer 📌 Input-output Alignment — keeping latent representations in-distribution 🚀 Training-free Collaboration — plug-and-play with existing LLMs Why it matters: ✅ Up to +14.6% better accuracy on complex reasoning tasks ⚡ 4-4.6x faster end-to-end inference ✂️ 70.8%–83.7% reduction in output token usage A step toward multi-agent systems that collaborate not by speaking more, but by thinking together in latent space. #MultiAgentSystems# #ModelCollaboration# #LatentReasoning# #LLM# #AgenticAI# #ICML#

GLM5.2发布后证明了我一直以来的观点，中国模型（开源模型）在coding上只落后美国模型（闭源模型）6-8个月。 但是要知道Fable 5强的地方不是Coding能力（这方面它甚至和Opus4.8在一个水平），而是规划能力。 这也是完成Loop的重要能力（甚至是自动递归），这个差距可能来自于Anthropic模型范式的改进（latent reasoning）。 现在中美的Neo Lab们都在对这个峰顶进行冲刺。