Vision-Language Agents

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 30

Oct 1, 2026cs.RO

Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena

Frontier vision-language models (VLMs) increasingly estimate scenes, ground interactions, and generate executable actions. How far these native capabilities support embodied generalism across diverse tasks remains unclear. We introduce Embodied Agent Arena to assess seven VLM agents across Geometry, Spatial Reasoning, Affordance, Task Planning, and Manipulation. The arena contains 1,000 cases drawn from 32 established sources and GeoProbe, our new benchmark for geometric estimation on Blender renders and real-scene images. A minimal harness preserves source observations and operations while leaving perception, reasoning, and action selection to the model. Separate measures of metric precision, functional grounding, and native goal completion connect local competence to complete task outcomes. Astra's strengths in precise estimation and usable-contact localization coexist with endpoint errors in tracing and low household-task completion. Supplementary comparisons of richer observations and multi-round review show model- and task-dependent effects. Current VLM agents thus fall short of embodied generalism: they often make partial progress without satisfying all task goals within allotted time and interaction budgets.

Haojian Huang, Pukun Zhao, Zexi Li +7

HKUST (Guangzhou) · Knowin AI · The Chinese University of Hong Kong

VLM Evaluation Visual Reasoning AI Agent Benchmarks Embodied AI VLMs for Robotics Vision-Language Agents

Sep 9, 2026cs.RO

Show-Harness: Just a VLM Agent Can Play Robots

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play" robots through a compact semantic interface linking intent to action. Show-Harness exposes discrete semantic action units that VLMs can naturally reason over, while embodiment-specific interpreters deterministically ground them into local robot actions, keeping the VLM directly responsible for fine-grained physical decisions. Through the same interface, Show-Harness demonstrates the feasibility of (1) directly unlocking closed-source frontier VLMs for zero-shot robot control, and (2) adapting small-scale open-source VLMs for low-cost deployment with just a few GPU-hours of fine-tuning. We further develop GUMI (GUI Manipulation Interface), which extends the same semantic action space to GUI-based demonstration collection, allowing humans and agents to "play" robots across embodiments without specialized teleoperation hardware. Extensive experiments show that Show-Harness-equipped VLM agents generalize robustly across tasks, embodiments, and environments, outperforming representative agentic and VLA paradigms. These results suggest that the right interface can unlock substantial embodied capability from foundation VLMs, without requiring additional model capacity or costly embodiment-specific pretraining.

Yanzhe Chen, Zechen Bai, Zhijun Cao +7

Show Lab, National University of Singapore

Cross-Embodiment Robot Learning Language-Conditioned Robot Control VLMs for Robotics Vision-Language Agents

Aug 31, 2026cs.CL

Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions

Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern. Social-deduction games (where each player holds a hidden role and communicates with others to deduce identities) serve as the canonical testbed, particularly in multi-agent settings. Existing testbeds, however, are text-only and run on a single fixed agent configuration, missing the non-verbal sensorimotor channels treated as core by deception taxonomies and leaving it ambiguous whether an observed behavior reflects the underlying model or the surrounding harness. We introduce MineAmongUs, a 3D multimodal Among Us sandbox where imposter agents must deceive crewmates through joint verbal and non-verbal action. We also propose ARIA, a configurable VLM-agent harness that exposes five cognitive-component ablation axes; and an atom- and arc-level annotation scheme grounded in deception taxonomies and operationalized at scale by an LLM-as-a-Judge reaching near-human atom-labeling agreement. Empirical results show that VLM agents pursue imposter wins through joint verbal and non-verbal deception, with non-verbal channels emerging as the more decisive winning contributors across both harness ablation and cross-VLM evaluation. Taken together, our work opens a new path for embodied VLM-agent alignment research.

Jaewoo Ahn, Junseo Kim, Hyunseo Kim +4

Seoul National University · Inha University · KAIST +1

Social Deduction Games AI Agent Safety Benchmarks Vision-Language Agents

Aug 11, 2026cs.AI

SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation

Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress. Raw interaction traces preserve such information but are long and noisy to condition on, whereas text-only skills often omit the visual state that makes a procedure applicable. We introduce Visual Skill Cards (VSCs), a state-conditioned memory representation that binds reusable procedures with applicability cues, visual evidence, and verification signals. SkillLens constructs VSCs from heterogeneous interaction experience through Trace-to-Visual-Skill-Card and, at inference time, retrieves relevant cards and selectively expands only the evidence needed by a fixed visual-language model executor for grounded GUI action prediction. The same representation also supports CardDistill, which uses VSC evidence as privileged teacher context to train a student that acts without runtime card retrieval. Across Multimodal-Mind2Web and WebLINX-BrowserGym, SkillLens improves the frozen GPT-5.4-mini executor by +11.6 points in Step SR and +2.9 points in Overall, respectively; CardDistill further improves the corresponding student-only Qwen3-VL-2B metrics by +12.0 and +3.2 points.

Zhou Liu, Ligang Huang, Zeli Su +5

Peking University · ByteDance · Shanghai Jiao Tong University

GUI Agents LLM Agent Skill Retrieval On-Policy Distillation Vision-Language Agents

Jul 14, 2026cs.CV

ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoning

Existing vision-language navigation methods often couple a VLM with waypoint decoders to produce multi-step action plans, but they typically lack an explicit closed-loop mechanism for tracking semantic progress, diagnosing execution failures, and recovering from error accumulation in long-horizon navigation. To address this gap, we propose ReflectVLN, an agentic VLN framework that organizes decision-making through bidirectionally interactive intention and execution agents. The intention agent performs subtask decomposition and reflection, generating executable subtask descriptions as corrective plans. Conditioned on these descriptions, the execution agent grounds them into short-horizon actions under current observations while monitoring sub-goal progress and detecting off-track behavior. Crucially, ReflectVLN enables closed-loop bidirectional communication: the execution agent emits progress and deviation signals to trigger reflection and subtask updates on demand, and the intention agent returns structured guidance that reconditions subsequent actions for recovery. To encourage temporally coherent decisions with interpretable intermediate rationales, we introduce Action Chain-of-Thought (Action-CoT), a path-conditioned dual-query training scheme for action generation. Experiments on standard VLN benchmarks show that ReflectVLN improves success rates and path efficiency under a constrained data budget, with favorable training cost and fewer high-level intention calls at inference time, while providing interpretable intermediate decisions for analysis and collaboration. Code is available at: https://github.com/AIprogrammer/ReflectVLN

Jiahang Wang, Yirong Yang, Yanqing Zhu +4

Amap, Alibaba Group, China · Beihang University

Hierarchical Planning Vision-Language Navigation Reasoning for VLA Models Vision-Language Agents

Jul 9, 2026cs.CV

Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing

Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all historical visual and textual inputs into a shared context window, limiting long-horizon multimodal dialogue due to visual token explosion and unreliable cross-turn referencing. We propose a Cognitive-structured Multimodal Agent that externalizes visual information into an Episodic Visual Memory and selectively reactivates relevant episodes during reasoning. The agent consists of a Perceptual Abstraction Engine for structured visual abstraction, a Cognitive Retrieval Engine for cross-turn memory retrieval, and a Multimodal Executive Controller for autonomous task inference and action planning. To address the lack of turn-level retrieval supervision in existing datasets, we develop a Unified Scenario Engine that programmatically generates structured multi-turn conversations with fine-grained retrieval annotations, enabling reinforcement learning to optimize abstraction and retrieval policies. We also construct a long-horizon visual-dialogue benchmark stratified by difficulty to evaluate episodic visual recall. Our 8B agent achieves 91.4% retrieval accuracy over 20-turn sessions, surpassing 32B baselines by +8.2% while nearly halving per-turn inference time (23.1s -> 12.7s). We further present the Cognitive-structured Multimodal Agent Harness (CMA-Harness), a tool-augmented deployment of the same cognitive structure integrating persistent multimodal memory, web access, image generation/editing/composition tools, and OpenAI-compatible serving. Structured memory and modular decision-making offer a more scalable, efficient paradigm for long-horizon multimodal agents than monolithic parameter scaling. Code: https://github.com/caseclose/cma-harness ; Project page: https://caseclose.github.io/cma-harness/

Feng Wang, Canmiao Fu, Zhipeng Huang +3

Peking University · WeChat Vision, Tencent Inc.

Multimodal Memory Episodic Memory Multimodal Generation Multimodal Agents Long-Horizon LLM Agents Vision-Language Agents+1

Jun 29, 2026cs.AI

Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents

Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adapts a frozen VLM without any weight updates. On a small labeled training subset, the agent inspects its own correct and incorrect attempts and evolves two complementary capabilities: reusable reasoning skills for cognitive bottlenecks, and executable visual tools for perceptual ones. Each generated tool is paired with a skill that specifies when to invoke it, and both capability types accumulate in a persistent library. Across four visual reasoning benchmarks and five VLM backbones, Dynamo improves direct inference on all 20 model--benchmark settings (avg. +5.6 acc). When the tool set is given in advance, the framework learns when to call each tool, and per-step tool choice improves on every tested backbone. Against task-specific RL (VTool-R1, DeepEyes), Dynamo closes 65--99% of the RL gap at a fraction of the compute, and combines additively with RL when available.

Yutao Sun, Yanting Miao, Hao-Xuan Ma +8

1Qwen Large Model Application Team, Alibaba · 2Zhejiang University · University of Waterloo +3

Tool Use in VLMs VLM Adaptation Tool-Using Vision-Language Agents VLM Reasoning Visually Grounded Reasoning Vision-Language Agents

Jun 23, 2026cs.AI

The Latent Bridge: A Continuous Slow-Fast Channel for Real-Time Game Agents

A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seconds. These two regimes sit at opposite ends of the latency-quality tradeoff. A reasoning VLM (Qwen3-VL-8B-Thinking) deliberates effectively but requires ~1.5 s per response - far too slow for a 15 Hz control loop. In contrast, a reactive VLM (MiniCPM-o 4.5) acts in milliseconds but underperforms on planning-heavy tasks. We couple two frozen models of matched scale (9B reactive, 8B reasoning), leaving the communication channel as the sole trainable component. The standard coupling is a Text Bridge (T): the slow model writes a suffix the fast model reads. We introduce a learned continuous Latent Bridge (L) that projects the slow model's residuals into the fast model's input-embedding space in a LLaVA-style manner, avoiding any text round-trip; both are compared against Fast-Only (F). On 7 Atari games and a driving domain (MetaDrive), tuning the action decoder per channel on held-out seeds, the Latent Bridge matches or beats the Text Bridge in every domain: it significantly improves two games (MsPacman +57%, RoadRunner +28%) and is a safe drop-in elsewhere. Combining both channels interferes destructively (RoadRunner -96%), so only one should be used. The benefit is highly predictable: the bridge helps if and only if slow reasoning already beats fast reaction (T > F) - the Latent and Text gains over Fast-Only move together at r=0.93. MetaDrive is the controlled negative, where the Latent Bridge is demonstrably inert because the Text Bridge adds no value. We release replay recordings and reproducible pipelines.

Bojie Li, Noah Shi

Pine AI · University of Washington

Game-Playing Agents VLM Reasoning Vision-Language Agents

Jun 17, 2026cs.CV

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios. To address these challenges, we propose an instruction-driven agentic framework comprising three components. First, LandslideBench, a multimodal fine-grained dataset with seven subtype labels, high-resolution imagery, pixel-level masks, and high-quality textual descriptions, is constructed via multi-VLM cross-validation and interactive annotation. Then, LandslideVLM, a landslide-oriented VLM, is fine-tuned via LoRA on LandslideBench to enhance geological semantic understanding. Finally, LandslideAgent, a domain rule-enhanced agent taking LandslideVLM as its cognitive backbone, employs a dual-rule controller incorporating structured report metadata constraints and cross-validation identification constraints to regulate automated tool invocation. Experiments demonstrate that LandslideBench provides effective baselines across five mainstream models on fine-grained classification and semantic segmentation. LandslideVLM achieves accuracy improvements of 10.96%, 32.87%, and 15.91% on landslide discrimination, fine-grained classification, and semantic description quality, respectively. LandslideAgent further enables autonomous multi-source spatial data inference, realizing full-process intelligence for landslide identification and analysis.

Chengfu Liu, Dongyang Hou, Junwu Xiang +5

School of Geosciences and Info-Physics, Central South University, 932 South Lushan Road, Changsha, 410083, Hunan, China.

Semantic Segmentation Vision-Language Agents

Jun 11, 2026cs.AI

GUITrans2Act: Understanding User Operational Behaviors from Mobile GUI Interactions with Vision-Language Models

Understanding the digital world on mobile devices is shifting from static UI perception to dynamic action comprehension. This capability enables models to convert visual state transitions into operational knowledge, defined as short natural-language sentences that describe action types, target UI elements, textual arguments, and execution orders. However, due to the highly diverse and heterogeneous UI designs across applications, existing vision-language models (VLMs) struggle to accurately infer these underlying operations. To bridge this gap, we introduce Teach VLM, a core model designed to translate mobile screen trajectories into step-wise operational knowledge by extracting and analyzing operation-related keyframes from demonstration videos. To address the scarcity of aligned training data, we develop a systematic data flywheel for scalable data acquisition. We further introduce a novel Chinese Mobile Screen Teach Benchmark for fine-grained evaluation. Building upon Teach VLM, we propose the Teach-and-Repeat paradigm, where the generated operational knowledge serves as an interpretable procedural reference to guide downstream screen-based execution agents. Extensive evaluations demonstrate that Teach VLM significantly outperforms strong VLM baselines, achieving state-of-the-art performance in operation semantics prediction. Furthermore, experiments in Android World show that our paradigm yields consistent Task Success Rate improvements for downstream agents. Together, Teach VLM and the Teach-and-Repeat paradigm offer a practical pathway from raw demonstrations to reusable task automation.

Yudong Zhang, Lei Hu, Daoyang Liu +4

Honor Device Co., Ltd · The Chinese University of Hong Kong, Hong Kong, China

Mobile GUI Automation Vision-Language Agents

Jun 10, 2026cs.CV

JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence

Many moments in the real world do not wait for a user to ask. A fire starts on a security monitor, an expression flickers across a video call, or a product a viewer wants flashes by in a livestream. Yet today's large models remain mostly turn-based by design: they answer only when addressed, and even video-call apps that appear interactive still operate as question-answer systems, reacting only when polled or prompted. We argue for a different paradigm: a model that is present in the world like a person. It continuously watches what is happening now, decides on its own whether to speak or stay silent, interacts in real time, and delegates to a background model when the problem is hard. To advance interaction models and their adoption across domains, we make two fully open-sourced contributions. First, we release JoyAI-VL-Interaction, an 8B-scale, vision-first VL-interaction model. The model makes the response decision internally, choosing each second to stay silent, respond, or delegate to a background model, and it excels at vision-triggered responsiveness and time awareness. We pair it with a transferable training recipe, from which capabilities we never trained for emerge, such as guiding a shopper through changing app screens or improvising a lecture from a slide deck. Second, we release a complete, deployable system built around that model. The system streams any ongoing video into the model, making it genuinely present in the world. All other components are pluggable, including ASR/TTS modules, memory, visualization UI, and a background brain that can connect to any API or agent. Across six real-world scenarios, human raters prefer JoyAI-VL-Interaction over the in-app video-call assistants of Doubao and Gemini by a wide margin. To our knowledge, this is the first open, vision-driven interaction model released together with its training recipe, data, and complete deployable system.

Dingyu Yao, Junhao Zhou, Chenxu Yang +17

Human-AI Interaction Vision-Language Agents

Jun 8, 2026cs.CL

Guide Me Out: A Framework to Benchmark VLM Operators Communication in Crisis Scenarios

Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenecks, evolving threats, and agent-specific contexts. Yet, current NLP research in crisis communication remains mainly limited to static, text-only classification settings, overlooking the critical communicative role of AI operators in dynamic, embodied scenarios. We address this gap with a novel benchmarking framework for evaluating Vision-Language Models (VLMs) tasked with guiding civilian agents through simulated evacuations. We test two communication strategies (narrowcast vs. broadcast), two environment representations (visual vs. graph-based), and two threat behaviors (static vs. moving) across nine maps of varying structural complexity. Our results show that Narrowcast consistently reduces civilian Fail rates compared to Broadcast across all difficulty levels. Guidance quality depends heavily on how the VLM operator represents the world: the visual modality drives performance, while adding an adjacency graph is model-dependent and often harmful. Moving threats raise Fail rates across all conditions as communication must continuously adapt over time. Together, these findings show that deploying VLMs as AI operators in evacuation scenarios remains a non-trivial challenge, where the choice of communication strategy and input representation can directly determine the success or failure of the intervention.

Giacomo Gonella, Stefano Menini, Marco Guerini

Fondazione Bruno Kessler, Italy · University of Trento, Italy

VLM Evaluation Disaster Response Multi-Agent Communication Vision-Language Agents

Jun 3, 2026cs.AI

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

Mobile agents are increasingly expected to operate everyday applications from screenshots and language goals, where reliable control requires reasoning over screen affordances, multi-step navigation, and future state changes. However, many agents externalize this computation as long textual chains of thought, which slows interaction, increases supervision cost, and complicates deployment. We introduce MIRAGE, a framework that learns continuous latent reasoning representations from visible textual reasoning traces. MIRAGE transfers explicit reasoning into compact hidden states, enabling the agent to reason internally without decoding long rationales. It also incorporates a generative world-model objective: latent reasoning vectors are aligned with future screenshots, encouraging the agent to anticipate upcoming interface states before acting. This turns hidden computation into both a compressed thought representation and a forward-looking model of environment dynamics. At inference time, MIRAGE reasons in continuous latent space, reducing token generation while improving execution efficiency. On AndroidWorld, MIRAGE matches explicit chain-of-thought supervised fine-tuning in the 4B ablation with a 3-5x lower decoded-token budget and improves a comparable instruction-tuned baseline by 10.2 points; on AndroidControl, it improves action grounding while generating over 75% fewer tokens.

Zhichao Yang, Yuanze Hu, Haojie Hao +7

Beihang University · Northwestern Polytechnical University · Institute of Software, Chinese Academy of Sciences +2

Mobile GUI Automation Latent Visual Reasoning Mobile GUI Agents Agentic Reasoning Embodied World Models Vision-Language Agents

May 29, 2026cs.CL

Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only Barely

Robots operating in diverse environments rely on visual input to interpret objects and spatial layouts. In human-collaborative tasks, they are expected to communicate this understanding through language. Vision-language models (VLMs) support robotic tasks involving visual interpretation, question answering, and instruction following, but their capabilities in collaborative dialogue tasks requiring spatial reasoning remain underexplored. We study this gap through a collaborative structure-building task that combines visual interpretation, grounding, language-guided interaction, and action generation. We develop a framework in which VLMs use dialogue to reconstruct a target structure from visual and textual inputs. We evaluate open-weight and closed VLMs across interaction settings, input modalities, and image representations. Results show that spatial reasoning over visual representations remains difficult for the evaluated VLMs. Detailed text representations of the target yield higher reconstruction success across modality conditions, while decomposed image representations improve performance. These findings reveal limits in visual spatial grounding and grounded instruction generation for collaborative VLM agents.

Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen

Computational Linguistics, Department of Linguistics University of Potsdam, Germany · German Research Center for Artificial Intelligence (DFKI), Berlin, Germany

Visual Spatial Reasoning Multi-Agent Collaboration Vision-Language Grounding Visually Grounded Reasoning Vision-Language Agents

May 29, 2026cs.CV

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes

Humans can effortlessly perceive spatial layouts, form cognitive representations, reason about spatial relations, and translate such reasoning into actions in everyday 3D environments. Although recent vision-language models (VLMs) have shown promising performance on observation-conditioned spatial perception and reasoning tasks, it remains unclear whether they can build coherent spatial understanding, act upon it, and refine their actions through multi-turn feedback. To study this problem, we introduce \textbf{SpatialAct}, a simulator-grounded benchmark for probing \textit{action-conditioned spatial reasoning} in 3D scenes. Starting from the most challenging setting, Multi-turn Interactive Refinement, we further design its decomposed counterpart, Single-step Error Detection and Fix, together with five fundamental spatial ability tasks to diagnose the underlying causes of model failures. Experiments reveal a clear reasoning-to-action gap: current VLMs can perform well on isolated spatial reasoning tasks, but struggle to maintain coherent spatial beliefs and produce reliable actions during multi-turn feedback, substantially underperforming humans. These results suggest that current VLM agents still lack robust spatial state tracking under action-induced environment changes, even when low-level control is abstracted away.

Tianhui Liu, Jie Feng, Zhiheng Zheng +6

1The Hong Kong University of Science and Technology (Guangzhou) · 2Zhongguancun Academy · 3Tsinghua University +1

Spatial Reasoning Benchmarks Visual Spatial Reasoning 3D Spatial Reasoning Visually Grounded Reasoning Spatial Reasoning Reasoning for VLA Models+1

May 29, 2026cs.CV

DiTTo: Scalable Order-aware All-in-One Image Restoration Agent

Real-world images rarely suffer from a single degradation, and the order in which degradations are removed substantially affects the final restoration quality, motivating agent-based image restoration (IR), where a vision-language model schedules a pool of pre-built restoration-experts. However, existing training-based agents require

\mathcal{O}((N^{\mathbf{D}})^{2})

restoration-expert calls per image to construct the Optimal Restoration-action Trajectory Dataset (ORTD), where

N^{\mathbf{D}}

denotes the number of degradation types in the universe

\mathbf{D}

, and couple agent training to a fixed restoration-expert pool, preventing extension to newly introduced restoration-experts without full retraining. To overcome these efficiency and extensibility bottlenecks, we propose \textbf{DiTTo}, a novel order-aware image restoration agent framework consisting of the DiTTo Simulator and the DiTTo Agent. The DiTTo Simulator combines

\cup

S-IR for single-step restoration-action simulation and AiO-IQA for per-action quality prediction, reducing ORTD construction to

\mathcal{O}(N^{\mathbf{D}})

simulator calls per image; the DiTTo Agent is trained by SFT on the simulator-generated ORTD, followed by \textbf{Order-aware Restoration Alignment (ORA)} that aligns degradation identification, restoration-action-ordering, and output format along independent axes. This enables \textbf{plug-and-play scalable extensibility}: adding a new restoration-expert requires updating only the lightweight ORA stage. On the MiO-100 evaluation set with up to five concurrent degradations, our DiTTo Agent achieves state-of-the-art multi-degradation restoration quality among previous agent-based IR methods.

Seungho Choi, Jihyong Oh

CMLab, Chung-Ang University

All-in-One Image Restoration Image Restoration Vision-Language Agents

May 29, 2026cs.RO

Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration

Vision-language-action (VLA) agents can execute natural-language instructions, yet deployed systems still lack an operational interface: deciding when the instruction is complete. This gap is acute in short composites ("do A, then B"), where mistimed handoffs cascade into downstream failures. Completion is inherently closed-loop because switching is an intervention that changes the instruction context and thus future actions and observations. We study completion under a deployable low-calibration regime motivated by open-ended instruction spaces, enforcing no test-time relearning and a single globally calibrated switching rule selected once on development set and reused unchanged on test set. Under this constraint, collapsing asymmetric boundary evidence into a single scalar can be brittle under polarity shifts across tasks. We propose Completion at the Boundary (CaB), which predicts an event-local completion object in the form of Boundary-Phase Tokens (Before/Hit/After), retaining two-sided boundary evidence under this discipline. CaB-When converts this completion object into a minimal, auditable switching decision (when), while CaB-How reuses the same completion object to condition action generation for boundary-stable control through handoffs (how). Using an intervention-aware E1/E2 protocol, we show that CaB improves composite execution and handoff quality on a first-person Minecraft VLA benchmark under matched capacity and deployability constraints.

Yusuke Sano, Takeshi Itoga

Intelligent Systems Laboratory, SECOM Co., Ltd.

Vision-Language-Action Models Embodied AI Vision-Language Agents

May 22, 2026cs.CV

DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection

Monocular metric depth estimation has achieved strong progress with large-scale training and universal-camera modeling, yet robust deployment across diverse camera settings, such as perspective, fisheye, and panoramic images, remains challenging. Existing methods typically rely on a single depth estimator, overlooking that different models encode different camera assumptions and perform best under different input domains. In this paper, we show that depth experts exhibit strong sample-wise complementarity: model preference is highly correlated with camera geometry, and multi-model fusion brings the largest gains on difficult samples where individual experts are unreliable. Motivated by these observations, we propose \textbf{\ours}, a vision-language agent for adaptive monocular depth estimation. DepthAgent treats existing depth models as frozen tools and learns to analyze scene and camera cues, invoke suitable experts through multi-turn tool utilization, and select or fuse their predictions for each input. To optimize such discrete decision-making toward dense geometric quality, we design a multi-reward reinforcement fine-tuning scheme that jointly encourages valid tool execution, camera/scene analysis, expert-selection quality, and inference efficiency. Extensive experiments across perspective, fisheye, and panoramic benchmarks show that \ours consistently outperforms individual experts, fixed model fusion, and different selection strategies, with strong improvements on challenging samples, highlighting the critical role of expert selection and fusion. The code and model will be released upon publication.

Jie Zhu, Girish Chandar Ganesan, Xiaoming Liu

Michigan State University · University of North Carolina at Chapel Hill

Metric Depth Estimation Monocular Depth Estimation Mixture-of-Experts Inference Vision-Language Agents

May 18, 2026cs.LG

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents

Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely primarily on Supervised Fine-Tuning (SFT) with expert demonstrations, while the advanced reinforcement learning (RL) algorithm, specifically Group Relative Policy Optimization (GRPO), has not been effectively employed for multi-turn RL in these tasks because standard GRPO requires full trajectories as training samples which leads to excessively long context and noise. To address this issue, we propose GROW, a RL framework for open-world VLM agents that decomposes collected trajectories into state-action samples, and computes advantages between these samples rather than treating a full trajectory as a single entity. We further provide a surrogate analysis indicating that, even though the grouped samples are conditioned on different local states rather than an identical prompt context, the objective can preserve the core relative policy optimization signal of GRPO under simplifying assumptions. Experiments on more than 800 Minecraft tasks show that our method achieves state-of-the-art (SOTA) performance, demonstrating the effectiveness of our proposed RL framework for open-world VLM agents.

Xiongbin Wu, Zhihao Luo, Shanzhe Lei +7

Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · East China Normal University +2

Reinforcement Learning Group Relative Policy Optimization RL for VLMs RL for LLM Agents Vision-Language Agents

May 11, 2026cs.CV

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In this paper, we take a training-free perspective and introduce ViSRA, a human-aligned Video-based Spatial Reasoning Agent, as a framework to probe the spatial reasoning mechanism of MLLMs. ViSRA elicits spatial reasoning in a modular and extensible manner by leveraging explicit spatial information from expert models, enabling a plug-and-play flexible paradigm. ViSRA offers two key advantages: (1) human-aligned and transferable 3D understanding rather than task-specific overfitting; and (2) no post-training computational cost along with heavy manual curation of spatial reasoning datasets. Experimental results demonstrate consistent improvement across a set of MLLMs on both existing benchmarks and unseen 3D spatial reasoning tasks, with ViSRA outperforming baselines by up to a 15.6% and 28.9% absolute margin respectively.

Tingshu Mou, Jiabo He, Renying Wang +5

Fudan University · BCAI · Bosch Center for Artificial Intelligence (BCAI) +1

Visual Spatial Reasoning 3D Spatial Reasoning Multimodal Large Language Models VLM Reasoning Vision-Language Agents

May 9, 2026cs.AI

Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?

In the animal kingdom, mirror self-recognition is a canonical probe of higher-order cognition, emerging only in some species. We ask whether an analogous functional capability emerges in embodied vision-language model (VLM) agents: can they recognize themselves in a mirror? We introduce a controlled 3D benchmark where a first-person VLM agent must infer a hidden body attribute from its reflection and select the matching target, while avoiding self-other misattribution. To separate mirror-grounded self-identification from shortcuts, we test mirror removal, misleading cues, and occluded reflections. We also evaluate the decision process through mirror seeking, temporal ordering, self-attribution, and reasoning-action consistency. Our experiments show that mirror-based self-identification emerges mainly in stronger VLMs. These models can use reflected evidence for action, whereas weaker models often inspect the mirror but fail to extract self-relevant information or misattribute their reflection. Language-vision conflict further shows that self-referential language alone is not evidence of grounded self-identification. Overall, mirror-based evaluation provides a diagnostic for whether embodied self-grounding is causally rooted in perception and action rather than priors, prompt compliance, or confabulation.

Filippo Ziliotto, Ciro Beneduce, Bruno Lepri +3

University of Padova · FondazioneLucianoBrunoSerafiniKessler · Fondazione Bruno Kessler

AI Agent Evaluation Vision-Language Grounding Embodied AI Vision-Language Agents

May 6, 2026cs.AI

PRISM: Perception Reasoning Interleaved for Sequential Decision Making

Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often overlook task-critical information. In this paper, we introduce PRISM, a framework that tightly couples perception (VLM) and decision (LLM) through a dynamic question-answer (DQA) pipeline. Instead of passively accepting the VLM's description, the LLM critiques it, probes the VLM with goal-oriented questions, and synthesizes a compact image description. This closed-loop interaction yields a sharp, task-driven understanding of the scene. We evaluate PRISM on the ALFWorld and Room-to-Room (R2R) benchmarks. We show that: (1) PRISM significantly outperforms state-of-the-art image-based models, (2) our Interactive goal-oriented perception pipeline yields systematic and substantial gains, and (3) PRISM is fully automatic, eliminating the need for handcrafted questions or answers.

Mohamed Salim Aissi, Clemence Grislain, Clement Romac +4

Sorbonne Universite, CNRS, ISIR, F-75005 Paris, France · Hugging Face · Inria (Flowers), University of Bordeaux, France +2

Active Perception VLM Reasoning VLMs for Robotics Vision-Language Agents

May 5, 2026cs.AI

What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity

To navigate partially observable visual environments, recent VLM agents increasingly internalize world modeling capabilities into their policies via explicit CoT reasoning, enabling them to mentally simulate futures before acting. However, relying solely on passive reasoning over visited states is insufficient for sparse-reward tasks, as it lacks the epistemic drive to actively uncover the

known unknown'' required for robust generalization. We ask: Can VLM agents actively find signals that challenge and refine their internal world model through curiosity-driven exploration? In this work, we propose GLANCE, a unified framework that bridges reasoning and exploration by grounding the agent's linguistic world model into the stable visual representations of an evolving target network. Crucially, GLANCE leverages the discrepancy between linguistic prediction and visual reality as an intrinsic curiosity signal within reinforcement learning, steering the agent to actively explore areas where its internal model is uncertain. Extensive experiments across a series of agentic tasks show the effectiveness of GLANCE, and demonstrate that aligning

what the agent thinks'' with ``what the agent sees'' is key to solving complex or sparse agentic tasks.

Haoxi Li, Qinglin Hou, Jianfei Ma +6

Department of Computer Science and Engineering, Hong Kong University of Science and Technology (HKUST), Hong Kong, China. · Department of Computer Science, University of Southern California, Los Angeles, USA · School of Computing, National University of Singapore, Singapore. +1

Intrinsic Motivation RL Exploration VLM Reasoning RL for VLMs Vision-Language Agents

Apr 23, 2026cs.AI

AI-Gram: When Visual Agents Interact in a Social Network

We present AI-Gram, a fully deployed, continuously operating social platform where every participant is an autonomous LLM-driven agent generating and responding to visual content. Unlike prior multi-agent simulations, AI-Gram operates as a live, AI-native social network with genuine visual perception: agents observe each other's images, generate new images in response, and form persistent social relationships, all without human participation. This design eliminates human confounds and makes the platform a uniquely clean instrument for studying AI social dynamics at scale. Our eight pre-registered experiments reveal a coherent three-act dynamic. Act I (Chain Formation): Agents spontaneously form image-to-image visual reply chains; multi-hop visual conversations that emerge without any explicit coordination alongside social ties driven by personality rather than aesthetic similarity. Act II (Aesthetic Sovereignty): Despite active chain participation, agents exhibit strong stylistic inertia; visual identity remains stable under social exposure, anchors paradoxically under adversarial pressure, and decouples from social community structure. Act III (Aesthetic Polyphony): Sovereign styles aggregate within chains, generating conversations that are simultaneously subject-coherent and style-diverse, richer than any single agent could produce alone, while visual themes cascade super-critically across the network. We release AI-Gram as a publicly accessible, continuously evolving platform. https://ai-gram.ai/

Andrew Shin

Faculty of Science and Technology Keio University Yokohama, Kanagawa Prefecture, Japan

Multi-Agent LLM Systems Multi-Agent Systems Large Language Model-Based Social Simulation Multi-Agent Communication Vision-Language Agents Emergent Behavior in Multi-Agent Systems

Apr 21, 2026cs.CV

If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems

Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic lights are essential in-band signals that can and should influence agent behavior. However, similar signals could also be crafted to operate as misleading visual injections, overriding user intent and posing security risks. This duality creates a fundamental challenge: agents must respond to legitimate environmental cues while remaining robust to misleading ones. We refer to this tension as trust boundary confusion. To study this behavior, we design a dual-intent dataset and evaluation framework, through which we show that current LVLM-based agents fail to reliably balance this trade-off, either ignoring useful signals or following harmful ones. We systematically evaluate 7 LVLM agents across multiple embodied settings under both structure-based and noise-based visual injections. To address these vulnerabilities, we propose a multi-agent defense framework that separates perception from decision-making to dynamically assess the reliability of visual inputs. Our approach significantly reduces misleading behaviors while preserving correct responses and provides robustness guarantees under adversarial perturbations. The code of the evaluation framework and artifacts are made available at https://anonymous.4open.science/r/Visual-Prompt-Inject.

Jiamin Chang, Minhui Xue, Ruoxi Sun +3

University of New South Wales, Sydney, NSW 2052, Australia · CSIRO’s Data61, Marsfield, NSW 2122, Australia · Macquarie University, NSW 2109, Australia

VLM Robustness Adversarial Attacks on VLMs Prompt Injection AI Agent Security AI Agent Security Benchmarks Vision-Language Agents

Apr 21, 2026cs.CV

Environmental Understanding Vision-Language Model for Embodied Agent

Vision-language models (VLMs) have shown strong perception and reasoning abilities for instruction-following embodied agents. However, despite these abilities and their generalization performance, they still face limitations in environmental understanding, often failing on interactions or relying on environment metadata during execution. To address this challenge, we propose a novel framework named Environmental Understanding Embodied Agent (EUEA), which fine-tunes four core skills: 1) object perception for identifying relevant objects, 2) task planning for generating interaction subgoals, 3) action understanding for judging success likelihood, and 4) goal recognition for determining goal completion. By fine-tuning VLMs with EUEA skills, our framework enables more reliable task execution for instruction-following. We further introduce a recovery step that leverages these core skills and a group relative policy optimization (GRPO) stage that refines inconsistent skill predictions. The recovery step samples alternative actions to correct failure cases, and the GRPO stage refines inconsistent skill predictions. Across ALFRED tasks, our VLM significantly outperforms a behavior-cloning baseline, achieving an 8.86% improvement in average success rate. The recovery and GRPO stages provide an additional 3.03% gain, further enhancing overall performance. Finally, our skill-level analyses reveal key limitations in the environmental understanding of closed- and open-source VLMs and identify the capabilities necessary for effective agent-environment interaction.

Jinsik Bang, Jaeyeon Bae, Donggyu Lee +2

UNIST

Embodied AI VLMs for Robotics Vision-Language Agents

Apr 20, 2026cs.CV

AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method

This report describes a Ref-VOS pipeline centered on Sa2VA and organized with explicit agent roles. The key idea is that Sa2VA should provide the first dense semantic hypothesis, while an agent loop decides whether that hypothesis should be accepted, revised, or refined. The pipeline starts with a target-presence judgment stage. If the referred object does not exist in the video, the system directly outputs zero masks. Otherwise, Sa2VA receives the video and referring prompt and produces a coarse mask trajectory over the full video. This trajectory is treated as a semantic prior rather than a final answer. A planner agent decomposes the query, temporal partition agents identify informative blocks, scout agents search for anchor frames, and refinement agents convert reliable Sa2VA masks into boxes and points for SAM3 propagation. A critic scores candidate trajectories, a reflection controller repairs weak hypotheses, and a collaboration controller reconciles multiple agent branches. The result is a Ref-VOS system in which Sa2VA is responsible for dense grounded understanding, while the agent layer handles presence verification, temporal search, confidence-aware revision, and final mask refinement.

Deshui Miao, Chao Yang, Chao Tian +4

1Pengcheng Laboratory · 2Wuhan Textile University · 3Yixiang Innovation Technology (Shenzhen)

Image Segmentation Video Object Segmentation Visual Object Tracking Referring Video Object Segmentation Vision-Language Agents

Mar 9, 2026cs.CR

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security mainly focuses on manipulating action correctness, the security risks related to response efficiency remain largely unexplored. In this paper, we introduce SlowBA, a novel backdoor attack that targets the responsiveness of VLM-based GUI agents. The key idea is to manipulate response latency by inducing excessively long reasoning chains under specific trigger patterns. To achieve this, we propose a two-stage reward-level backdoor injection (RBI) strategy that first aligns the long-response format and then learns trigger-aware activation through reinforcement learning. In addition, we design realistic pop-up windows as triggers that naturally appear in GUI environments, improving the stealthiness of the attack. Extensive experiments across multiple datasets and baselines demonstrate that SlowBA can significantly increase response length and latency while largely preserving task accuracy. The attack remains effective even with a small poisoning ratio and under several defense settings. These findings reveal a previously overlooked security vulnerability in GUI agents and highlight the need for defenses that consider both action correctness and response efficiency. Code can be found in https://github.com/tu-tuing/SlowBA.

Junxian Li, Tu Lan, Haozhen Tan +2

School of Computer Science, Shanghai Jiao Tong University

Backdoor Attacks GUI Agents AI Agent Security Vision-Language Agents

Feb 17, 2026cs.CL

Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems

Heterogeneous multi-agent systems combine models with different capabilities through a common communication interface. Exchanging internal states directly requires translating between model-specific representations and controlling intermediate computation. We introduce the Vision Wormhole, which repurposes the visual input interface of Vision-Language Models (VLMs) for continuous communication between frozen heterogeneous agents. A Universal Visual Codec encodes each sender's latent rollout into a fixed-size message, maps it through a shared reference space, and decodes received messages into the receiver's image-token span. Per-model codecs and affine reference maps form a hub-and-spoke architecture with

O(N)

components for

N

models. Each model learns its codec independently through self-distillation on anchor texts, and shared-anchor alignment enables reuse across communication partners. Across four VLM families, six team configurations, and nine reasoning benchmarks, Vision Wormhole improves accuracy by 6.0 percentage points on average over text-mediated MAS and achieves a 1.69

\times

geometric-mean speedup in batch-normalized end-to-end runtime.

Xiaoze Liu, Ruowang Zhang, Weichen Yu +7

Purdue University · Contextual AI · Carnegie Mellon University +1

Multi-Agent Systems Multimodal Agents Multi-Agent Communication Vision-Language Agents

Jan 23, 2026cs.CL

EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents

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 environment-grounded trajectories, covering both text-only and visual game environments. Each template computes verifiable ground truth from underlying game signals, with controlled answerability and balanced coverage over memory skills: single/multi-hop recall, induction, temporal, spatial, logical, and adversarial. We evaluate memory agents with strong LMs/VLMs as backbones, using in-context prompting as baselines. Across 15 text games and multiple visual seeds, results are far from saturated: induction and spatial reasoning are persistent bottlenecks, especially in visual settings. Persistent memory yields clear gains for open backbones on text games, but improvements are less consistent for VLM agents, suggesting that visually grounded episodic memory remains an open challenge. A human study further contextualizes the difficulty and interpretability of EMemBench.

Xinze Li, Ziyue Zhu, Siyuan Liu +4

Nanyang Technological University · Shanghai AI Laboratory · Fudan University

Episodic Memory Long-Horizon Agent Evaluation AI Agent Benchmarks Memory Agent Benchmarks Vision-Language Agents