mlsanityData to 7 Oct 2026

VIVA+: Human-Centered Situational Decision-Making

arXiv 2509.23698 ↗First posted 28 Sep 2025cs.CLcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Multimodal Large Language Models (MLLMs) show promising results for embodied agents in operating meaningfully in complex, human-centered environments. Yet, evaluating their capacity for nuanced, human-like reasoning and decision-making remains challenging. In this work, we introduce VIVA+, a cognitively grounded benchmark for evaluating the reasoning and decision-making of MLLMs in human-centered situations. VIVA+ consists of 1,317 real-world situations paired with 6,373 multiple-choice questions, targeting three core abilities for decision-making: (1) Foundational Situation Comprehension, (2) Context-Driven Action Justification, and (3) Reflective Reasoning. Together, these dimensions provide a systematic framework for assessing a model's ability to perceive, reason, and act in socially meaningful ways. We evaluate the latest commercial and open-source models on VIVA+, where we reveal distinct performance patterns and highlight significant challenges. We further explore targeted training and multi-step reasoning strategies, which yield consistent performance improvements. Finally, our in-depth analysis highlights current model limitations and provides actionable insights for advancing MLLMs toward more robust, context-aware, and socially adept decision-making in real-world settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 33 of its 49 references that are in the map. First posted on arXiv 28 Sep 2025.

Builds on

33 of 49 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning21 Mar
  2. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents13 Feb
  3. 2024PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain21 Feb
  4. 2023Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond3 Oct

Other references · 29

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  3. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  4. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 553
  5. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  6. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  7. 2024MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIcited by 192
  8. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  9. 2025Cosmos-Reason1: From Physical Common Sense To Embodied Reasoningcited by 159
  10. 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Makingcited by 142
  11. 2025Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectivescited by 120
  12. 2019Counterfactual Story Reasoning and Generationcited by 87
17 more
  1. 2024Pandora: Towards General World Model with Natural Language Actions and Video Statescited by 83
  2. 2025SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attributioncited by 68
  3. 2023Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planningcited by 59
  4. 2024DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Lifecited by 57
  5. 2024Multimodal Situational Safetycited by 54
  6. 2024A Survey on Robotics with Foundation Models: toward Embodied AIcited by 53
  7. 2023Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AIcited by 23
  8. 2024VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Modelscited by 23
  9. 2023UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situationscited by 19
  10. 2025Embodied Scene Understanding for Vision Language Models via MetaVQAcited by 16
  11. 2025EgoNormia: Benchmarking Physical Social Norm Understandingcited by 13
  12. 2024VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Valuescited by 12
  13. 2024Emerging Practices for Large Multimodal Model (LMM) Assistance for People with Visual Impairments: Implications for Designcited by 10
  14. 2025CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectivescited by 10
  15. 2024HighwayLLM: Decision-Making and Navigation in Highway Driving with RL-Informed Language Modelcited by 9
  16. 2024E2CL: Exploration-based Error Correction Learning for Embodied Agentscited by 9
  17. 2025Empowering LLMs in Decision Games through Algorithmic Data Synthesiscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs
  2. 2025Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents
  3. 2025HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context
  4. 2025Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans
  5. 2026Improving Behavioral Alignment in LLM Social Simulations via Context Formation and Navigation
  6. 2023Understanding Social Reasoning in Language Models with Language Models
  7. 2024Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions
  8. 2025Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly