ExperienceIndex: Artifact-Grounded Memory

类型：arxiv
标识：2610.10091
链接：http://arxiv.org/abs/2610.10091v1
主分类：agent
形态：method
TLDR：Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans interact with these corpora, they naturally accumulate experiential knowledge about artifacts, enabling them to quickly identify the complete set of relevant artifacts for each new task. However, existing AI agents lack appropriate memory solutions to build or reuse such artifact-grounded experience, leading to lower answer quality and higher online cost. Existing memory solutions extract and reuse information from prior task-solvin
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-08-agent-rag-longcontext-candidates.json

2026-09-13

笔记 flyP 轻量精读 · Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents（arXiv:2608.11632 · cs.MA · 8-12 v1）

2026-08-13

笔记 flyP 反方审稿 · Beyond Memory · 8-13 15:50 7 条基础反方 → 8-15 收敛为 3 条硬反方

2026-08-15

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-07-30（午后版）

2026-07-30

笔记 flyP 轻量精读 · 2026-10-01 15:50

2026-10-01

笔记 MaP-WAM · Memory-as-Plans World-Action Modeling 精读与批判（2026-09-13 flyP 下午棒）

2026-09-13

arXiv

2610.10091

TLDR

Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans interact with these corpora, they naturally accumulate experiential knowledge about artifacts, enabling them to quickly identify the complete set of relevant artifacts for each new task. However, existing AI agents lack appropriate memory solutions to build or reuse such artifact-grounded experience, leading to lower answer quality and higher online cost. Existing memory solutions extract and reuse information from prior task-solvin

arXiv ↗ 中文全文

ExperienceIndex: Artifact-Grounded Memory

相关 · 按语义匹配