English(EN)LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger
AI溯源框架利用结构化账本和圣训科学
作者PulseAugur 编辑部·[6 个来源]·
两篇新研究论文提出用于增强AI系统可靠性和溯源性的新颖框架。第一篇，LedgerMind，引入了一个受溯源约束的状态机，用于多模态代理，以确保推理基于证据并检测幻觉等问题。第二篇，Isnad-Rijal，改编了古典伊斯兰圣训科学方法论，为多代理知识系统中的叙述者可靠性和主张溯源性创建了一个评分系统，旨在提高可信度。
AI
arXiv:2607.28374v1 Announce Type: new Abstract: Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy. This aggregate sign…
Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy. This aggregate signal cannot tell whether a correct answer was reac…
Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy. This aggregate signal cannot tell whether a correct answer was reac…
arXiv:2607.24117v1 Announce Type: new Abstract: Modern multi-agent knowledge systems increasingly accumulate knowledge through chains of autonomous transformations rather than direct retrieval. Existing provenance work records what happened - execution traces, tool calls, evidenc…
Modern multi-agent knowledge systems increasingly accumulate knowledge through chains of autonomous transformations rather than direct retrieval. Existing provenance work records what happened - execution traces, tool calls, evidence links - and source-reliability estimation is l…
Modern multi-agent knowledge systems increasingly accumulate knowledge through chains of autonomous transformations rather than direct retrieval. Existing provenance work records what happened - execution traces, tool calls, evidence links - and source-reliability estimation is l…
