A trainable memory system that distills memory construction into a small model and uses a GRPO-trained summarizer to improve answer quality per unit inference cost in long-horizon agent conversations.
M$^3$Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Language agents are increasingly deployed over accumulating multimodal information, yet existing benchmarks assume a human-human form with sparse visuals and straightforward content, evaluating neither reasoning over authentic multimodal file interaction nor the interpretation of concealed user information. We therefore introduce M$^3$Exam, a query-centric multimodal conversational memory benchmark built on realistic user-agent interaction, with multi-dimensional evaluation spanning cross-modal grounding and implicit information inference. Benchmarking MLLMs and memory systems reveals persistent gaps in cross-modal grounding, cross session reasoning, and the efficiency cost of accumulating multimodal context. We further propose M$^3$Proctor, a multimodal memory method that detects query modality bias and consumes raw visual sources only on demand, improving accuracy by 13% while cutting index-construction time and retrieved tokens by over 70%.
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
A trainable memory system that distills memory construction into a small model and uses a GRPO-trained summarizer to improve answer quality per unit inference cost in long-horizon agent conversations.