paper-with-me

Papers

SituationalLLM: Proactive language models with scene awareness for dynamic, contextual task guidance

2024-06-19 · Muhammad Saif Ullah Khan, Muhammad Zeshan Afzal, Didier Stricker

Large language models (LLMs) have achieved remarkable success in text-based tasks but often struggle to provide actionable guidance in real-world physical environments. This is because of their inability to recognize their limited understanding of the user's physical context. We present SituationalLLM, a novel approach that integrates structured scene information into an LLM to deliver proactive, context-aware assistance. By encoding objects, attributes, and relationships in a custom Scene Graph Language, SituationalLLM actively identifies gaps in environmental context and seeks clarifications during user interactions. This behavior emerges from training on the Situational Awareness Database for Instruct-Tuning (SAD-Instruct), which combines diverse, scenario-specific scene graphs with iterative, dialogue-based refinements. Experimental results indicate that SituationalLLM outperforms generic LLM baselines in task specificity, reliability, and adaptability, paving the way for environment-aware AI assistants capable of delivering robust, user-centric guidance under real-world constraints.

📄 PDF Abstract BibTeX arXiv:2406.13302

Code (1)

saifkhichi96/situational-llm 공식 구현

Tasks

Decision MakingLanguage ModelingLarge Language ModelSpecificity

Similar Papers 제목 키워드 기반

Evaluating Proactive Risk Awareness of Large Language Models

2026-02-24 · Xuan Luo, Yubin Chen, Zhiyu Hou, Linpu Yu 외 arxiv

As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward anticipating unintended but consequential risk…

Learning to Navigate Socially Through Proactive Risk Perception

2025-10-09 · Erjia Xiao, Lingfeng Zhang, Yingbo Tang, Hao Cheng 외 arxiv

In this report, we describe the technical details of our submission to the IROS 2025 RoboSense Challenge Social Navigation Track. This track focuses on developing RGBD-based perception and navigation systems that enable …

Collision Avoidance

Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent

2025-08-15 · Che Rin Yu, Daewon Chae, Dabin Seo, Sangwon Lee 외 arxiv

When humans perform everyday tasks, we naturally adjust our actions based on the current state of the environment. For instance, if we intend to put something into a drawer but notice it is closed, we open it first. Howe…

Language as Cost: Proactive Hazard Mapping using VLM for Robot Navigation

2025-08-05 · Mintaek Oh, Chan Kim, Seung-Woo Seo, Seong-Woo Kim arxiv

Robots operating in human-centric or hazardous environments must proactively anticipate and mitigate dangers beyond basic obstacle detection. Traditional navigation systems often depend on static maps, which struggle to …

Robot Navigation

LLM-SAP: Large Language Models Situational Awareness Based Planning

2023-12-26 · Liman Wang, Hanyang Zhong

This study explores integrating large language models (LLMs) with situational awareness-based planning (SAP) to enhance the decision-making capabilities of AI agents in dynamic and uncertain environments. We employ a mul…

Decision MakingLanguage ModellingLarge Language Model