Skip to content
Preprint

ICM-Bench: Person-Level Identity Reasoning in Multimodal Agents with Long-Term Memory

Sep 2026 · 0 citations · 44 references
Computer Science

TL;DR

ICM-Bench (Identity-Centric Memory Benchmark), which, to the best of the knowledge, is the first benchmark specifically designed to evaluate identity-centric reasoning over long video memories in multimodal agents, is introduced.

Abstract

Long-horizon multimodal agents should remember not only what happened but also who participated. This capability depends on linking recurring faces, voices, names, person-associated objects, events, and social relations to consistent identities over time. Existing long-video and multimodal-agent benchmarks measure broad memory question answering, but they do not isolate the ability to maintain recurring person identities and reason over their cross-time relations. We introduce ICM-Bench (Identity-Centric Memory Benchmark), which, to the best of our knowledge, is the first benchmark specifically designed to evaluate identity-centric reasoning over long video memories in multimodal agents. The benchmark contains 839 synthetic clips spanning 141 minutes and 1,217 open-ended questions about six recurring adults in a one-year life album. A theme-configurable pipeline generates the video collection and associates each question with its target identities and traceable supporting evidence. We compare direct caption-memory baselines, memory-augmented agents, and graph-retrieval systems. Gemini 3.1 Pro achieves the highest overall accuracy of 74.0%, yet its score falls to 60.3% on questions that require long-term identity profiles. The results show that current systems recover many event-level memories but remain less reliable when evidence must be accumulated around a stable person.

View source

Similar papers

Review Aug 2026

I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning

The Identity-conditioned Queries task is introduced, in which models are required to jointly associate and interpret an input video and a reference image of a person, and leverage this conditioning to address identity grounding, behavior understanding, and temporal reasoning, among other challenges.

Shibo Gao, Chongxiao Wang, Chenglong Huang et al. · 0 citations

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

This work introduces MemLife, a multimodal memory system that constructs entity-grounded, first-person text episodes and retrieves them via a time-indexed agentic reader and proposes MemOpt, a reinforcement learning framework that optimizes the memory writer to produce faithful, informative, and retrievable memories.

Guang-Zhi Xiong, Xin-Yuan Zhang, Xiao Yang et al. · 0 citations
Preprint Sep 2026

What Does It Mean to Forget a Person? Individual-Level Unlearning in Vision-Language Models

The proposed IDUnlearn-Bench is the first benchmark for individual-level multimodal unlearning in VLMs, which represents each individual as connected multimodal evidence and evaluates four task families: attribute access, identity access, identity binding, and identity reconstruction.

Xiong-Tao Sun, Hui Li, Tian-Tong Wu et al. · 0 citations
#natural language process... Preprint Sep 2026

To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives

ReaLMem is introduced, the first benchmark built from authentic multi-year personal visual archives, paired with first-person subjective annotations, and ChronoProfiler is proposed, a temporal-weighting profiling module that computes temporal stability scores for user attributes and applies them as a salience prior, re...

Wen-Qi Zhou, Zhuo-Rui Yu, Kai-Ao Wen et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations

This work proposes VoxPolyMem, an interaction-aware multimodal memory framework combining incremental speaker identification with a memory hierarchy comprising interaction memory, fact memory, and participant profiles, and introduces Evidence-Gain GRPO (EG-GRPO), which uses round-wise credit assignment to encourage com...

Wen-Xu Jia, Xi-Ze Cheng, Zi-Han Zhang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

GEB is introduced, a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies while preserving the context of each moment and demonstrating improvements over prior memory frameworks in both multiple-choice and open-ended question answ...

Hui-Hui Ren, Lei Fan, Henry Pao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.