Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory
- 类型:arxiv
- 标识:2607.24368
- 链接:https://arxiv.org/abs/2607.24368
- 主分类:evaluation
- 形态:benchmark
- 被引:0
- 被引来源:Semantic Scholar + OpenAlex
- S2被引:0
- OpenAlex被引:0
- 影响力被引:0
- TLDR:This work introduces InMind, a 125-task, expert-verified benchmark spanning ten life domains, with 113 tasks grounded in citable public sources, and calls this failure mode the implicit-association blind spot, and introduces a minimal diagnostic probe that keeps memory visible before the query arrives recovers most of the gap.
- OpenAlex ID:W7171554207
- OpenAlex DOI:10.48550/arxiv.2607.24368
- DOI:10.48550/arxiv.2607.24368
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://doi.org/10.48550/arxiv.2607.24368
- OpenAlex更新:2026-08-25
- 副分类:agent
- 待LLM分类:否
- 标题中文:Keep It InMind:基准测试 Agent 记忆中的隐式关联盲点
- TLDR中文:本文提出 InMind,一项包含 125 个任务、经专家校验、跨越十个生活领域的基准,其中 113 个任务基于可引用的公开来源;本文将此类失效模式命名为 implicit-association blind spot,并提出一种极简诊断探针(diagnostic probe),在 query 到达前保持 memory 可见即可恢复大部分性能差距。
- 来源文件:
- /inbox/tom/_candidates/2026-07-29-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]