arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
arXiv:2609.05539v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have recently made strong progress in vision-language reasoning, yet their performance often degrades as gen...
arXiv:2601.16690v2 Announce Type: replace Abstract: We introduce EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games. Rather tha...
arXiv:2602. 00471v2 Announce Type: replace Abstract: While Visual Multi-Agent Systems (VMAS) promise to enhance comprehensive abilities through inter-agent collaboration, empirical evidence reveals a counter-intuitive "scaling wall": increasing agent turns often degrades performance while exponentially inflating token costs.
The paper presents a comprehensive evaluation of 11 memory substrates for long‑horizon LLM agents, using a unified set of 26 performance and efficiency metrics across three backbone models and four benchmark suites. It finds that no single substrate consistently outperforms others; retrieval‑heavy substrates aid long‑context factual QA but can impair sequential decision‑making, and scalability can shift performance trade‑offs. The study demonstrates that selecting a memory substrate tailored to the operating regime yields better results than any fixed choice, offering empirical guidance for designing efficient, reliable, and regime‑aware long‑term memory systems.
MemoryArena is a new evaluation gym that benchmarks agent memory in interdependent multi‑session tasks. Unlike prior benchmarks that test memorization or single‑session action in isolation, MemoryArena requires agents to acquire memory while interacting with the environment and then use that memory to guide future decisions across a range of tasks such as web navigation, planning, information search, and formal reasoning. The benchmark reveals that agents excelling on existing long‑context memory tests perform poorly here, highlighting a gap in current memory evaluation methods.
The paper introduces AutoMMemo, a framework that lets agents automatically design memory mechanisms for learning from multimodal experience. Each memory mechanism is represented as an executable memo program that specifies how past episodes are stored, organized, and retrieved. Through iterative evaluation, reflection-guided mutation, and budget-aware tree search, AutoMMemo learns effective memory designs that improve agent performance on GUI/Web navigation and multimodal visual reasoning tasks while keeping token and interaction costs reasonable.
arXiv:2608. 10525v1 Announce Type: cross Abstract: Historical context integration presents a fundamental challenge for Vision-Language Models (VLMs) in sequential decision-making tasks.
arXiv:2610.08630v1 Announce Type: new Abstract: Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, u...
GUIFlow is a framework that enables temporal redundancy‑aware incremental inference for GUI agents built on vision‑language models. By selectively updating computational states—such as position‑aligned KV states, vision encoder outputs, and language model drafts—across interaction steps, it allows cross‑step reuse of visual encoding, prefill, and decoding without extra training or model changes. Experiments show up to 3.39× speedup on offline benchmarks and 3.49× in online OSWorld interactions while preserving task performance.
arXiv:2607. 17621v1 Announce Type: new Abstract: Existing self-evolving memory systems mainly improve agent memory based on textual outputs, such as task trajectories and reflections.
arXiv:2606. 27499v1 Announce Type: cross Abstract: Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when an agent genuinely needs to remember what it saw rather than what it could write down.