Challenge: Existing safety evaluations focus on hazard recognition through disembodied question answering (QA) settings, but lack a critical gap in evaluating an agent.
Approach: They evaluate multimodal large language models with six categories of kitchen hazards . they propose a safety-based approach that prioritizes multi-step corrective actions .
Outcome: The proposed model can recognize hazards in QA settings, but average mitigation success rates are low . the proposed model is based on the embodied agent benchmark ALFRED .

Similar Papers

When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life (2026.findings-acl)

Copied to clipboard

Challenge: Safety impact of Multimodal Large Language Models (MLLMs) on human behavior is evaluated in this study.
Approach: They propose a safety-warning-based evaluation framework that encourages models to provide clear and informative safety warnings, rather than generic refusals.
Outcome: The proposed safety-warning-based evaluation framework encourages models to provide clear and informative safety warnings, rather than generic refusals.
Can’t See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs (2025.acl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images.
Approach: They propose a multimodal safety awareness benchmark to evaluate MLLMs across 29 safety scenarios with 1,500 carefully curated image-prompt pairs.
Outcome: The proposed model is able to identify unsafe content and avoid over-sensitivity that can hinder helpfulness.
MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning (2026.findings-acl)

Copied to clipboard

Challenge: Existing safety alignment methods, such as RLHF, fall into a Safety-Utility Trade-off, resulting in severe over-rejection of benign household instructions.
Approach: They propose a meta-cognitive Critical Agent that evaluates peer debates using a structured argumentation framework derived from the Toulmin Model.
Outcome: The proposed architecture outperforms existing systems in the SafeAware-VH benchmark.
Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making (2025.emnlp-main)

Copied to clipboard

Challenge: Existing safety evaluations rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these models fail.
Approach: They propose a framework for systematically evaluating the physical safety of LLMs in embodied decision making.
Outcome: The proposed framework assesses the physical safety of LLMs in embodied decision making.
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues (2026.findings-acl)

Copied to clipboard

Challenge: Existing contextual safety benchmarks are mostly single-turn and miss how malicious intent can emerge gradually or how the same scene can support both benign and exploitative goals.
Approach: They propose a benchmark that evaluates contextual safety in multimodal large language models . they observe persistent trade-offs between contextual safety and utility .
Outcome: The proposed model combines multi-turn and multi-switch scenarios to evaluate safety in multimodal large language models.
USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Copied to clipboard

Challenge: Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach: They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome: The proposed framework covers 61 risk categories across four distinct modality interactions.
VestaBench: An Embodied Benchmark for Safe Long-Horizon Planning Under Multi-Constraint and Adversarial Settings (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing safety benchmarks do not represent a diverse range of multi-constraint tasks that require long-horizon planning with a focus on safety.
Approach: They propose a benchmark to assess the safety of embodied AI agents under multiple constraints.
Outcome: The proposed benchmarks show that LLMs perform poorly against their tasks . they also suffer significantly compromised safety outcomes .
VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation Agents (2026.acl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models have demonstrated remarkable capabilities across vision-language tasks, but their performance as embodied agents needs further exploration.
Approach: They propose a framework to evaluate multimodal large language models as zero-shot agents . they find that enhancing prevalent agents with Chain-of-Thought reasoning and self-reflection leads to an unexpected performance decrease.
Outcome: The proposed framework enables comparisons and component-level ablations across diverse MLLM architectures, agent designs, and navigation tasks.
MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation frameworks assess isolated responses using coarse-grained taxonomies or static datasets.
Approach: They propose a role-aware mental health safety taxonomy that characterizes clinically significant harm in terms of interactional roles an AI counselor adopts.
Outcome: The proposed framework significantly improves failure-mode coverage and diagnostic granularity.
The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in multimodal reasoning may pose new safety risks . evaluators neglect reasoningbased safety, where harm emerges only through MLLMs .
Approach: They introduce a benchmark for multi-image reasoning safety that includes 2,676 instances . they find that models with more advanced multi- image reasoning are more vulnerable .
Outcome: The proposed benchmark consists of 2,676 instances covering 9 multi-image relations . the results show that models with more advanced multi- image reasoning are more vulnerable .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations