arXiv:2608. 08960v1 Announce Type: new Abstract: Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs.
FOVEA introduces a cache‑friendly, on‑demand visual evidence adaptation for multimodal speculative decoding, enabling a lightweight draft model to dynamically retrieve a bounded subset of visual memory based on a cumulative‑mass rule. The retrieved visual readout is fused with the draft hidden state via a lightweight gated residual correction, avoiding the insertion of visual tokens into the autoregressive context. Experiments on various vision‑language backbones and benchmarks show that FOVEA improves draft acceptance and speeds up end‑to‑end decoding by up to 2.13× compared to traditional autoregressive decoding.
arXiv:2609.23121v1 Announce Type: new Abstract: Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical framework...
UniMem is a framework that unifies visual and textual memory with low‑level control in a single Vision‑Language‑Action model, using an event classifier, keyframe encoder, and caching to manage memory efficiently. It addresses non‑Markovian tasks that require remembering past scenes, avoiding the memory bottleneck of separate VLMs and the performance drop from fixed‑interval frame sampling. Across five simulation and four hardware tasks, UniMem outperforms fixed‑interval sampling (93.4% vs. 68.2%) and hierarchical VLM‑VLA baselines (80.0% vs. 43.5%) while offering faster inference and a simpler training pipeline.
arXiv:2605.11212v4 Announce Type: replace Abstract: Computer-use agents (CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual...
VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with s...
The paper introduces ViMoD, a lightweight framework that dynamically manages visual memory for multimodal large language models. ViMoD uses Deformable Aggregation of Region-wise Tokens (DART) to create content‑adaptive coarse representations linked to recoverable fine tokens, and Temporal Routing for Adaptive Contextual Evidence (TRACE) to anticipate and adjust evidence needs during reasoning. On the Qwen3‑VL‑4B model, ViMoD achieves superior performance across eight reasoning benchmarks with only a 20% visual token budget and minimal additional parameters.
arXiv:2608. 07585v1 Announce Type: cross Abstract: Long-video understanding requires models to efficiently acquire and reuse sparse visual evidence from long and redundant video streams.
arXiv:2601.04786v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction,...
ECHOES is a method for long‑horizon GUI agents that compresses visual history into a textual state using a Compression‑Think‑Action format. It employs a privileged teacher model that provides token‑level on‑policy distillation to guide the student’s textual rollouts, while a Perception‑Memory Fidelity Gap‑guided framework balances distillation with task reward optimization. The approach is evaluated on four GUI benchmarks and a new ECHOESBMK diagnostic benchmark, showing improved task performance, memory fidelity, and a favorable trade‑off between performance and inference cost, with positive zero‑shot transfer to unseen planning tasks.
The paper introduces Caption‑once, Frames‑on‑Demand (CFD), a budget‑aware edge‑cloud framework for long‑video understanding. CFD first runs a single offline captioning pass on the edge to build a dual‑track narrative index—an event‑level story skeleton and a clip‑level micro‑log—that is cached for future queries. At query time, a cloud‑side MLLM uses a Visual‑Need Router to decide whether to retrieve keyframes for perceptual questions, thereby limiting visual processing while preserving temporal structure in language space.