Delegated Authorization for Agents Constrained to Semantic Task-to-Scope Matching

• URL: http://arxiv.org/abs/2510.26702v1
• Date: Thu, 30 Oct 2025 17:07:00 GMT
• Title: Delegated Authorization for Agents Constrained to Semantic Task-to-Scope Matching
• Abstract summary: Authorizing Large Language Model driven agents to dynamically invoke tools and access protected resources introduces significant risks.<n>We introduce and assess a delegated authorization model enabling authorization servers to semantically inspect access requests to protected resources.<n>Our results highlight the need for further research into semantic matching techniques enabling intent-aware authorization for multi-agent and tool-augmented applications.
• Score: 4.092829002386613
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Authorizing Large Language Model driven agents to dynamically invoke tools and access protected resources introduces significant risks, since current methods for delegating authorization grant overly broad permissions and give access to tools allowing agents to operate beyond the intended task scope. We introduce and assess a delegated authorization model enabling authorization servers to semantically inspect access requests to protected resources, and issue access tokens constrained to the minimal set of scopes necessary for the agents' assigned tasks. Given the unavailability of datasets centered on delegated authorization flows, particularly including both semantically appropriate and inappropriate scope requests for a given task, we introduce ASTRA, a dataset and data generation pipeline for benchmarking semantic matching between tasks and scopes. Our experiments show both the potential and current limitations of model-based matching, particularly as the number of scopes needed for task completion increases. Our results highlight the need for further research into semantic matching techniques enabling intent-aware authorization for multi-agent and tool-augmented applications, including fine-grained control, such as Task-Based Access Control (TBAC).

Related papers

• Authorization Architectures for Tool-Using AI Agents [0.0]
  Trustworthy human-AI systems require that every consequential agent action be traceable to a human principal.<n>This review introduces a principal hierarchy spanning human user, operator/deployer, orchestrator agent, sub-agent, and tool endpoint as an organizing framework.<n>We propose seven structural requirements, derive a four-layer reference architecture, apply the requirements to three deployable reference configurations, and identify runtime enforcement and aggregation bounds as the principal unresolved gaps.
  arXiv  Detail & Related papers  (2026-09-14T17:21:22Z)
• "Allow" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI Agents [38.29267974352746]
  We construct a four-level permission framework based on task relevance and privacy risk.<n>We evaluate four frontier multimodal large language models using synchronized annotated screenshots and UI-tree hierarchies.<n>Changing only the requester from Calendar to PiMusic reduces grants from 26/32 to 0/32, revealing a strong but task-conditioned App-Trust Bias.
  arXiv  Detail & Related papers  (2026-08-05T12:23:16Z)
• Testing Agentic Workflows with Structural Coverage Criteria [0.21485350418225244]
  We present a structural testing approach for multi-agent workflow specifications.<n>The approach represents each workflow as a typed coordination graph.<n>It derives coverage obligations over reachable agents, allowed tool edges, restricted tool edges, and delegation edges.
  arXiv  Detail & Related papers  (2026-05-26T04:07:55Z)
• Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI [4.092829002386613]
  A compromised or malicious agentic application can tamper with tool calls, falsify results, or request permissions beyond the scope of the subject's intended tasks.<n>We propose a hybrid runtime enforcement model that combines deterministic and semantic controls enabled by a zero-trust interception layer.<n>We generate novel conversation-tool datasets with multi-turn interactions containing relevant and irrelevant tool calls for a given task.
  arXiv  Detail & Related papers  (2026-05-04T15:00:37Z)
• AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation [71.49152943451328]
  We introduce a benchmark AJ-Bench to evaluate Agent-as-a-Judge across three domains-search, data systems, and graphical user interfaces-comprising 155 tasks and 516 annotated trajectories.<n>Experiments demonstrate consistent performance gains over LLM-as-a-Judge baselines, while also revealing substantial open challenges in agent-based verification.
  arXiv  Detail & Related papers  (2026-04-20T13:23:38Z)
• RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs [55.44696796126619]
  Earth Observation systems are designed to support domain experts who often express their requirements through vague natural language.<n>A practical EO AI system must bridge the gap between ambiguous human queries and the appropriate multi-granularity visual analysis tasks.<n>We propose RemoteAgent, an agentic framework that strategically respects the capability intrinsic boundaries of MLLMs.
  arXiv  Detail & Related papers  (2026-04-09T03:40:46Z)
• AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios [49.90735676070039]
  The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow.<n>We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks.<n>We propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks.
  arXiv  Detail & Related papers  (2026-01-28T13:49:18Z)
• Activation-Space Anchored Access Control for Multi-Class Permission Reasoning in Large Language Models [20.49818370567961]
  Large language models (LLMs) are increasingly deployed over knowledge bases for efficient knowledge retrieval and question answering.<n>LLMs can inadvertently answer beyond a user's permission scope, leaking sensitive content.<n>We propose Activation-space Anchored Access Control (AAAC), a training-free framework for multi-class permission control.
  arXiv  Detail & Related papers  (2026-01-20T05:57:44Z)
• Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL [0.15199492741752027]
  We propose an Information-Flow-Orchestrated Multi-Agent Paradigm via Agent-to-Agent (A2A) Communication.<n>We evaluate our approach on the general-purpose benchmark GAIA, using the representative workflow-based MAS as the baseline.<n>Our method achieves 63.64% accuracy, outperforming OWL's 55.15% by 8.49 percentage points with comparable token consumption.
  arXiv  Detail & Related papers  (2026-01-14T21:35:51Z)
• Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning [63.109585527799005]
  GroundingAgent is a visual grounding framework that operates without task-specific fine-tuning.<n>It achieves an average zero-shot grounding accuracy of 65.1 % on widely-used benchmarks.<n>It also offers strong interpretability, transparently illustrating each reasoning step.
  arXiv  Detail & Related papers  (2025-11-24T03:11:08Z)
• Authorization of Knowledge-base Agents in an Intent-based Management Function [0.07646713951724012]
  We propose an enhanced authorization framework that integrates roles and functional attributes with agent roles.<n>Our approach ensures that agents are granted only the minimal necessary privileges towards knowledge graphs.
  arXiv  Detail & Related papers  (2025-10-22T07:38:01Z)
• Authenticated Delegation and Authorized AI Agents [4.679384754914167]
  We introduce a novel framework for authenticated, authorized, and auditable delegation of authority to AI agents.<n>We propose a framework for translating flexible, natural language permissions into auditable access control configurations.
  arXiv  Detail & Related papers  (2025-01-16T17:11:21Z)
• An Ensemble Scheme for Proactive Dominant Data Migration of Pervasive Tasks at the Edge [5.4327243200369555]
  We propose a scheme to be implemented by autonomous edge nodes concerning their identifications of the appropriate data to be migrated to particular locations within the infrastructure. Our objective is to equip nodes with the capability to comprehend the access patterns relating to offloaded data-driven tasks. It is evident that these tasks depend on the processing of data that is absent from the original hosting nodes. To infer these data intervals, we utilize an ensemble approach that integrates a statistically oriented model and a machine learning framework.
  arXiv  Detail & Related papers  (2024-10-12T19:09:16Z)
• RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent [15.836845304125436]
  RS-Agent is an AI agent designed to interact with human users and autonomously leverage specialized models.<n> RS-Agent integrates four key components: a Central Controller based on large language models, a dynamic toolkit for tool execution, a Solution Space for task-specific expert guidance, and a Knowledge Space for domain-level reasoning.<n>Extensive experiments across 9 datasets and 18 remote sensing tasks demonstrate that RS-Agent significantly outperforms state-of-the-art MLLMs.
  arXiv  Detail & Related papers  (2024-06-11T09:30:02Z)
• Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents [110.25679611755962]
  Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. We introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. We empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals.
  arXiv  Detail & Related papers  (2024-02-14T14:36:30Z)
• Sparsity-Aware Intelligent Massive Random Access Control in Open RAN: A Reinforcement Learning Based Approach [61.74489383629319]
  Massive random access of devices in the emerging Open Radio Access Network (O-RAN) brings great challenge to the access control and management. reinforcement-learning (RL)-assisted scheme of closed-loop access control is proposed to preserve sparsity of access requests. Deep-RL-assisted SAUD is proposed to resolve highly complex environments with continuous and high-dimensional state and action spaces.
  arXiv  Detail & Related papers  (2023-03-05T12:25:49Z)
• Multi-agent Deep Covering Skill Discovery [50.812414209206054]
  We propose Multi-agent Deep Covering Option Discovery, which constructs the multi-agent options through minimizing the expected cover time of the multiple agents' joint state space. Also, we propose a novel framework to adopt the multi-agent options in the MARL process. We show that the proposed algorithm can effectively capture the agent interactions with the attention mechanism, successfully identify multi-agent options, and significantly outperforms prior works using single-agent options or no options.
  arXiv  Detail & Related papers  (2022-10-07T00:40:59Z)
• Provable Benefits of Representational Transfer in Reinforcement Learning [59.712501044999875]
  We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation. We show that given generative access to source tasks, we can discover a representation, using which subsequent linear RL techniques quickly converge to a near-optimal policy.
  arXiv  Detail & Related papers  (2022-05-29T04:31:29Z)
• Towards Inheritable Models for Open-Set Domain Adaptation [56.930641754944915]
  We introduce a practical Domain Adaptation paradigm where a source-trained model is used to facilitate adaptation in the absence of the source dataset in future. We present an objective way to quantify inheritability to enable the selection of the most suitable source model for a given target domain, even in the absence of the source data.
  arXiv  Detail & Related papers  (2020-04-09T07:16:30Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.