paper-with-me

Papers

Momento: Evaluating Persistent Memory and Reasoning with Multi-Session Agentic Conversations

2026-05-30 · Adril Putra Merin, David Anugraha, Ayu Purwarianti, Genta Indra Winata arxiv

Recent advances in agentic AI have enabled agents to complete complex tasks through tool use, reasoning, and multi-step planning. Yet existing benchmarks evaluate agents within a single session, ignoring past actions, stated preferences, and prior decisions that agents must integrate to fulfill personalized user goals. We introduce Momento, a benchmark for persistent agentic task completion in multi-session service environments, requiring agents to take consequential, tool-mediated actions while resolving temporal dependencies and evolving user goals across sessions. Experimental results reveal that current agents fail primarily through misestimation of user state, treating prior session history as a reliable proxy for current context rather than stale information requiring re-validation, highlighting a substantial gap between current agent capabilities and realistic long-horizon human-agent interaction.

📄 PDF Abstract BibTeX arXiv:2606.00832

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning

2024-02-18 · Long Qian, Juncheng Li, Yu Wu, Yaobo Ye 외

Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. How…

Language ModelingLanguage ModellingLarge Language Model

EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents

2026-01-23 · Xinze Li, Ziyue Zhu, Siyuan Liu, Yubo Ma 외 arxiv

We introduce EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generates questions from envi…

Spatial Reasoning

M$^3$Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions

2026-06-05 · Zhengjun Huang, Wenxuan Liu, Zhoujin Tian, Wei Chen 외 arxiv

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 aut…

Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents

2026-01-07 · Yuanchen Bei, Tianxin Wei, Xuying Ning, Yanjun Zhao 외 arxiv

Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over time. However, existing benchmarks eithe…

Test-time Adaptation

MEME: Multi-entity & Evolving Memory Evaluation

2026-05-12 · Seokwon Jung, Alexander Rubinstein, Arnas Uselis, Sangdoo Yun 외 arxiv

LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate only single-entity updates, MEME defines s…