Related papers: Integration of Large Vision Language Models for Efficient Post-disaster Damage Assessment and Reporting

Related papers

Task-Oriented Sensing and Covert Transmissions for Collaborative Multi-AUV Systems [67.63956000297922]
This paper proposes a Sensed Information Value Realization Multi-Agent Reinforcement Learning (SVR-MARL) framework to characterize the utility of information for cooperative tasks.<n>The potential of the proposed framework to improve collaborative task efficiency while reducing unnecessary communication and exposure risks is demonstrated.
arXiv Detail & Related papers (2026-07-15T14:29:25Z)
Latent Action Reparameterization for Efficient Agent Inference [56.42014061367112]
We propose a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior.<n>Unlike hand-crafted macros or hierarchical controllers, latent actions are learned from agent trajectories and integrated directly into the model.
arXiv Detail & Related papers (2026-05-18T16:07:44Z)
Resource Consumption Threats in Large Language Models [18.038172925174642]
Resource efficiency is a key requirement for large language models (LLMs)<n>Recent resource consumption threats induce excessive generation, degrading model efficiency and harming service availability and economic sustainability.<n>Our goal is to clarify the problem landscape for this emerging area, thereby providing a clearer foundation for characterization and mitigation.
arXiv Detail & Related papers (2026-03-17T02:35:04Z)
Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions [51.56484100374058]
Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes.<n>This gap, driven by mutually cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector.<n>This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure.
arXiv Detail & Related papers (2025-11-10T22:24:21Z)
An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue [11.300720465575608]
Large-scale disaster Search And Rescue (SAR) operations are persistently challenged by complex terrain and disrupted communications.<n>While Unmanned Aerial Vehicle (UAV) swarms offer a promising solution for tasks like wide-area search and supply delivery, yet their effective coordination places a significant cognitive burden on human operators.<n>This study proposes a novel LLM-CRF system that leverages Large Language Models (LLMs) to model and augment human-swarm teaming cognition.
arXiv Detail & Related papers (2025-11-06T04:27:20Z)
Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs [72.08224879435762]
textttLearn-to-Ask is a simulator-free framework for learning and deploying proactive dialogue agents.<n>Our approach culminates in the successful deployment of LLMs into a live, large-scale online AI service.
arXiv Detail & Related papers (2025-10-29T12:08:07Z)
Disaster Management in the Era of Agentic AI Systems: A Vision for Collective Human-Machine Intelligence for Augmented Resilience [13.155469498169866]
Disaster Copilot is a vision for a multi-agent artificial intelligence system designed to overcome these systemic challenges.<n>The proposed architecture utilizes a central orchestrator to coordinate diverse sub-agents, each specializing in critical domains such as predictive risk analytics, situational awareness, and impact assessment.
arXiv Detail & Related papers (2025-10-16T02:02:10Z)
ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning [53.065247112514534]
ATLAS is a general multi-agent framework designed to handle complex nature of constraints awareness in real-world travel planning tasks.<n>We demonstrate state-of-the-art performance on the TravelPlanner benchmark, improving the final pass rate from 23.3% to 44.4% over its best alternative.
arXiv Detail & Related papers (2025-09-29T23:23:52Z)
Less Redundancy: Boosting Practicality of Vision Language Model in Walking Assistants [18.21432204057241]
We propose WalkVLM-LR, a walking assistance model with less redundancy.<n>We introduce four human-preference-based custom reward functions within the GRPO-based reasoning framework to optimize the output.<n>Our method achieves state-of-the-art performance across all evaluation metrics compared with other models.
arXiv Detail & Related papers (2025-08-22T03:56:30Z)
Situational Awareness as the Imperative Capability for Disaster Resilience in the Era of Complex Hazards and Artificial Intelligence [1.1368819707015188]
Disasters frequently exceed established hazard models, revealing blind spots where unforeseen impacts and vulnerabilities hamper effective response.<n> situational awareness (SA)-the ability to perceive, interpret, and project dynamic crisis conditions-is an often overlooked yet vital capability for disaster resilience.
arXiv Detail & Related papers (2025-08-21T03:38:47Z)
Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
arXiv Detail & Related papers (2025-06-18T17:18:12Z)
IRCopilot: Automated Incident Response with Large Language Models [18.2902546324428]
Large Language Models (LLMs) have shown great potential in early threat detection.<n>Their capabilities remain limited when it comes to automated incident response after an intrusion.<n>We propose IRCopilot, a novel framework for automated incident response powered by LLMs.
arXiv Detail & Related papers (2025-05-27T09:29:11Z)
A Multi-Agent Reinforcement Learning Approach for Cooperative Air-Ground-Human Crowdsensing in Emergency Rescue [22.201769922727077]
This paper tackles the Heterogeneous Collaborative-Sensing Task Allocation problem for emergency rescue, considering humans, UAVs, and UGVs.<n>We introduce a novel Hard-Cooperative'' policy where UGVs prioritize recharging low-battery UAVs, alongside performing their sensing tasks.<n>We propose HECTA4ER, a novel multi-agent reinforcement learning algorithm built upon a Decentralized Execution architecture.
arXiv Detail & Related papers (2025-05-11T14:49:15Z)
EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning [69.55982246413046]
We propose explicit policy optimization (EPO) for strategic reasoning. EPO provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior. Experiments across social and physical domains demonstrate EPO's ability of long-term goal alignment.
arXiv Detail & Related papers (2025-02-18T03:15:55Z)
Self-Regulation and Requesting Interventions [63.5863047447313]
We propose an offline framework that trains a "helper" policy to request interventions. We score optimal intervention timing with PRMs and train the helper model on these labeled trajectories. This offline approach significantly reduces costly intervention calls during training.
arXiv Detail & Related papers (2025-02-07T00:06:17Z)
PSSD: Making Large Language Models Self-denial via Human Psyche Structure [5.057375783924452]
We present PSSD, which refers to and implements the human psyche structure such that three distinct and interconnected roles contribute to human reasoning. Extensive experiments demonstrate that the proposed design not only better enhance reasoning capabilities, but also seamlessly integrate with current models.
arXiv Detail & Related papers (2025-02-03T13:37:21Z)
Harnessing Large Language Models for Disaster Management: A Survey [57.00123968209682]
Large language models (LLMs) have revolutionized scientific research with their exceptional capabilities and transformed various fields. This study aims to guide the professional community in developing advanced LLMs for disaster management to enhance the resilience against natural disasters.
arXiv Detail & Related papers (2025-01-12T21:00:50Z)
Harnessing Language for Coordination: A Framework and Benchmark for LLM-Driven Multi-Agent Control [6.721923873906492]
Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. Their potential to facilitate human coordination with many agents is a promising but largely under-explored area. In this work, we introduce (1) a real-time strategy game benchmark designed to evaluate these abilities and (2) a novel framework we term HIVE.
arXiv Detail & Related papers (2024-12-16T13:25:42Z)
Efficient VoIP Communications through LLM-based Real-Time Speech Reconstruction and Call Prioritization for Emergency Services [0.0]
Emergency communication systems face disruptions due to packet loss, bandwidth constraints, poor signal quality, delays, and jitter in VoIP systems. Victims in distress often struggle to convey critical information due to panic, speech disorders, and background noise. This paper proposes leveraging Large Language Models (LLMs) to address these challenges by reconstructing incomplete speech, filling contextual gaps, and prioritizing calls based on severity.
arXiv Detail & Related papers (2024-12-09T17:22:40Z)
Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling [65.72918416258219]
Supportiveness-based Knowledge Rewriting (SKR) is a robust and pluggable knowledge rewriter inherently optimized for LLM generation. Based on knowledge supportiveness, we first design a training data curation strategy for our rewriter model. We then introduce the direct preference optimization (DPO) algorithm to align the generated rewrites to optimal supportiveness.
arXiv Detail & Related papers (2024-06-12T11:52:35Z)
LLM-Based Cooperative Agents using Information Relevance and Plan Validation [5.299803738642663]
Multi-agent cooperation involves interacting with a 3D scene and cooperating with decentralized agents under complex partial observations. Current systems demonstrate inefficiency in managing acquired information through observation. The failure to incorporate spatial data into decision-making processes restricts the agent's ability to construct optimized trajectories. We propose the RElevance and Validation-Enhanced Cooperative Language Agent (REVECA), a novel cognitive architecture powered by GPT-3.5.
arXiv Detail & Related papers (2024-05-27T01:47:14Z)
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
arXiv Detail & Related papers (2024-05-23T08:33:19Z)
KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models [53.84677081899392]
KIEval is a Knowledge-grounded Interactive Evaluation framework for large language models. It incorporates an LLM-powered "interactor" role for the first time to accomplish a dynamic contamination-resilient evaluation. Extensive experiments on seven leading LLMs across five datasets validate KIEval's effectiveness and generalization.
arXiv Detail & Related papers (2024-02-23T01:30:39Z)
The Stochastic Dynamic Post-Disaster Inventory Allocation Problem with Trucks and UAVs [1.3812010983144802]
Humanitarian logistics operations face increasing difficulties due to rising demands for aid in disaster areas. This paper investigates the dynamic allocation of scarce relief supplies across multiple affected districts over time. It introduces a novel dynamic post-disaster inventory allocation problem with trucks and unmanned aerial vehicles delivering relief goods.
arXiv Detail & Related papers (2023-11-30T19:03:04Z)
Proactive Resource Request for Disaster Response: A Deep Learning-based Optimization Model [0.2580765958706854]
We develop a new resource management problem that proactively decides optimal quantities of requested resources. We take salient characteristics of the problem into consideration and develop a novel deep learning method for future demand prediction. We demonstrate the superior performance of our method over prevalent existing methods using both real world and simulated data.
arXiv Detail & Related papers (2023-07-31T13:44:01Z)
Leveraging Domain Knowledge for Inclusive and Bias-aware Humanitarian Response Entry Classification [3.824858358548714]
We aim to provide an effective and ethically-aware system for humanitarian data analysis. We introduce a novel architecture adjusted to the humanitarian analysis framework. We also propose a systematic way to measure and biases.
arXiv Detail & Related papers (2023-05-26T09:15:05Z)
On the Risk of Misinformation Pollution with Large Language Models [127.1107824751703]
We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation in the performance of Open-Domain Question Answering (ODQA) systems.
arXiv Detail & Related papers (2023-05-23T04:10:26Z)
Persistent Reinforcement Learning via Subgoal Curricula [114.83989499740193]
Value-accelerated Persistent Reinforcement Learning (VaPRL) generates a curriculum of initial states. VaPRL reduces the interventions required by three orders of magnitude compared to episodic reinforcement learning.
arXiv Detail & Related papers (2021-07-27T16:39:45Z)
Efficient Strategy Synthesis for MDPs with Resource Constraints [16.774128823546416]
We consider strategy synthesis for the formalism called consumption Markov decision processes. The presented algorithms work in time with respect to the representation of the model.
arXiv Detail & Related papers (2021-05-05T14:59:30Z)
Bottom-up mechanism and improved contract net protocol for the dynamic task planning of heterogeneous Earth observation resources [61.75759893720484]
Earth observation resources are becoming increasingly indispensable in disaster relief, damage assessment and related domains. Many unpredicted factors, such as the change of observation task requirements, to the occurring of bad weather and resource failures, may cause the scheduled observation scheme to become infeasible. A bottom-up distributed coordinated framework together with an improved contract net are proposed to facilitate the dynamic task replanning for heterogeneous Earth observation resources.
arXiv Detail & Related papers (2020-07-13T03:51:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.