Author name cluster

Qineng Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

TMLR Journal 2026 Journal Article

ActionEQA: Action Interface for Embodied Question Answering

Tianwei Bao
Qineng Wang
Kangrui Wang
Mingkai Deng
Guangyi Liu
Jiayuan Mao
Lawrence Birnbaum
Zhiting Hu

While Vision-Language Models (VLMs) are increasingly integral to embodied intelligence, a significant action understanding bottleneck persists in translating high-level semantic instructions into precise low-level physical actions. However, current benchmarks for embodied agents primarily focus on high-level perception and planning, failing to capture the depth and nature of this semantic-to-physical gap. To address this, we introduce ActionEQA, the first Embodied Question Answering (EQA) benchmark designed to methodically evaluate the ability of VLMs to bridge this critical yet underexplored semantic-physical divide. Grounded in real-world robotics data, ActionEQA thoroughly analyzes VLMs’ grasp of the action interface using a dual-tier design: (1) a Three-Tiered Action Hierarchy for pinpointing the depth at which VLMs' action reasoning collapses. (2) Bidirectional Reasoning Tasks for testing whether VLMs struggle more to predict action outcomes or infer the actions that led to them. Our key findings reveal: (1) The primary bottleneck in action understanding occurs at the mid-level, arising from the challenge of grounding compositional language in 3D physical geometry. (2) VLMs are more adept at inferring past actions than predicting their future outcomes. (3) Richer visual inputs require greater spatial reasoning from VLMs to map actions to physical geometry. (4) Within the action hierarchy, model failures shift from predominantly perceptual errors at the high level to flawed geometric and physical reasoning at the low level.

PDF Details

ICML Conference 2025 Conference Paper

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Rui Yang 0010
Hanyang Chen
Junyu Zhang
Mark Zhao
Cheng Qian 0008
Kangrui Wang
Qineng Wang
Teja Venkat Koripella

Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents remain underexplored due to the lack of comprehensive evaluation frameworks. To bridge this gap, we introduce EmbodiedBench, an extensive benchmark designed to evaluate vision-driven embodied agents. EmbodiedBench features: (1) a diverse set of 1, 128 testing tasks across four environments, ranging from high-level semantic tasks (e. g. , household) to low-level tasks involving atomic actions (e. g. , navigation and manipulation); and (2) six meticulously curated subsets evaluating essential agent capabilities like commonsense reasoning, complex instruction understanding, spatial awareness, visual perception, and long-term planning. Through extensive experiments, we evaluated 24 leading proprietary and open-source MLLMs within EmbodiedBench. Our findings reveal that: MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only $28. 9\%$ on average. EmbodiedBench provides a multifaceted standardized evaluation platform that not only highlights existing challenges but also offers valuable insights to advance MLLM-based embodied agents. Our code and dataset are available at [https: //embodiedbench. github. io](https: //embodiedbench. github. io).

Details

NeurIPS Conference 2025 Conference Paper

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

Kangrui Wang
Pingyue Zhang
Zihan Wang
Yaning Gao
Linjie Li
Qineng Wang
Hanyang Chen
Yiping Lu

A major challenge in training VLM agents, compared to LLM agents, is that states shift from simple texts to complex visual observations, which introduces partial observability and demands robust world modeling. We ask: can VLM agents build internal world models through explicit visual state reasoning? In this work, we architecturally enforce and reward VLM agent’s reasoning process via reinforcement learning (RL), formulating the problem as a Partially Observable Markov Decision Process (POMDP). We demonstrate that structuring agent’s reasoning into StateEstimation (“what is the current state? ”) and TransitionModeling (“what is next? ”) is critical by studying five reasoning strategies. Investigating how agents should ground visual states and represent these internal beliefs, we reveal the optimal representations are task-dependent: Natural Language excels at capturing semantic relationships for general tasks, while Structured formats are essential for high-precision manipulation. These insights motivate our approach to reward shaping and credit assignment. We leverage a WorldModeling Reward to densely rewards the agent’s turn-by-turn state predictions, while our Bi-Level General Advantage Estimation (Bi-Level GAE) enables turn-aware credit assignment. Through such world model reasoning, we enable a 3B model to achieve performance of 0. 82 on a set of five diverse agent tasks, nearly 3× improvement over its untrained counterpart (0. 21) and surpassing proprietary reasoning models like GPT-5 (0. 75), Gemini 2. 5 Pro (0. 67) and Claude 4. 5 (0. 62). All experiments are supported by our VAGEN framework, a scalable system for training and analyzing multi-turn VLM agents across diverse visual environments

PDF Details

NeurIPS Conference 2024 Conference Paper

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making

Manling Li
Shiyu Zhao
Qineng Wang
Kangrui Wang
Yu Zhou
Sanjana Srivastava
Cem Gokmen
Tony Lee

We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their performance because they are usually applied in different domains, for different purposes, and built based on different inputs and outputs. Furthermore, existing evaluations tend to rely solely on a final success rate, making it difficult to pinpoint what ability is missing in LLMs and where the problem lies, which in turn blocks embodied agents from leveraging LLMs effectively and selectively. To address these limitations, we propose a generalized interface (Embodied Agent Interface) that supports the formalization of various types of tasks and input-output specifications of LLM-based modules. Specifically, it allows us to unify 1) a broad set of embodied decision-making tasks involving both state and temporally extended goals, 2) four commonly-used LLM-based modules for decision making: goal interpretation, subgoal decomposition, action sequencing, and transition modeling, and 3) a collection of fine-grained metrics that break down evaluation into error types, such as hallucination errors, affordance errors, and various types of planning errors. Overall, our benchmark offers a comprehensive assessment of LLMs’ performance for different subtasks, pinpointing the strengths and weaknesses in LLM-powered embodied AI systems and providing insights into the effective and selective use of LLMs in embodied decision making.

PDF Details DOI