- 资讯公开站rss_arxiv_cs_ai
DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents
arXiv:2610.02351v1 Announce Type: new Abstract: ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This coupling makes action …
- 资讯公开站rss_arxiv_cs_ai
Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs
arXiv:2610.00047v1 Announce Type: new Abstract: Diversity collapse in parallel chain-of-thought has motivated inference-time interventions built on a natural design: when a process reward model (PRM) prunes a chain, its…
- 资讯公开站rss_arxiv_cs_ai
Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits
arXiv:2609.38386v1 Announce Type: new Abstract: Concurrent autoregressive inference creates a fundamental interference problem: prefilling a newly arrived long prompt can delay tokens for requests that are already decod…
- 资讯公开站rss_arxiv_cs_ai
有效的大语言模型微调是否必须依赖人类可读文本？
Is Human-Readable Text Necessary for Effective LLM Fine-Tuning?
arXiv:2609.35868v1 公告类型：新 摘要：有效微调大语言模型是否必须依赖人类可读性？我们研究模型条件化的训练表示能否在无需人类可读文本形式的情况下保持或提升适配效用。我们提出 Desired-Update-Aligned Synthetic Data（DASA），利用冻结参考模型的激活梯度反馈来指导连续合成输入嵌入的优化。受激活梯度在局部风险降低中作用的启发，DASA 针对有用的适配更新，而非源文本重建或语言流畅性。所得…
- 资讯公开站Digitimes
Googlebook与QwenBook将智能体AI带入PC系统层，开启芯片新机遇
Googlebook, QwenBook bring agentic AI to the PC system layer, opening new chip opportunities
- 资讯公开站rss_arxiv_cs_ai
通过嵌入式编码改进大语言模型的医学计算能力
Improving Medical Calculation of LLMs with Embedded Coding
arXiv:2609.31908v1 公告类型：新 摘要：大语言模型（LLM）在医学考试和问答基准上表现良好，但在需要精确数值输出的医学计算任务上仍不可靠。这些计算支撑着用药剂量、器官功能评估和预后评分等高风险决策，即使很小的误差也可能带来严重的临床后果。我们提出 MedCode，一个通过训练 LLM 生成嵌入式可执行代码来改进医学计算的框架。给定临床情境，模型识别相关计算器，提取其输入变量，并生成一段将算术运算委托给确定性解释器的脚本…
