Papers

Filtered to retrieval evaluation · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

28 upvotes · 27 JUL 2026 · Ruizhe Li, Mingxuan Du, Benfeng Xu et al.

This paper evaluates how well AI systems can retrieve information from their memory when the information is related to but not directly connected to the query, and how this performance changes when the information is stored and then retrieved. Practitioners might care because understanding this blind spot can help improve the performance of AI systems in real-world applications.

agent memoryimplicit-associationmemory retrievalretrieval evaluationcontextualization