# REALM: Identifying Minimal Task Assets for LLM Agents

DevFeed: [REALM: Identifying Minimal Task Assets for LLM Agents](<https://devfeed.tech/articles/realm-identifying-minimal-task-assets-for-llm-agents-108158.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.39155>)

Author: Zihou Ren, Byungchul Tak, Long Wang

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [asr](<https://devfeed.tech/tags/asr.md>), [asset](<https://devfeed.tech/tags/asset.md>), [assets](<https://devfeed.tech/tags/assets.md>), [builder](<https://devfeed.tech/tags/builder.md>), [container](<https://devfeed.tech/tags/container.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [dependency-graph](<https://devfeed.tech/tags/dependency-graph.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [execution](<https://devfeed.tech/tags/execution.md>), [files](<https://devfeed.tech/tags/files.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [least-privilege](<https://devfeed.tech/tags/least-privilege.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [qwen3-5](<https://devfeed.tech/tags/qwen3-5.md>), [realm](<https://devfeed.tech/tags/realm.md>)

## AI overview

REALM limits an LLM agent's task access by tracking required assets and permitted uses in a dependency graph, resolving prerequisites, and admitting newly discovered assets through source-scoped selection. It separates asset discovery from authorization while leaving computation choices to the agent. The REALM Builder maintains grants and projects Asset Files; a Partial API Manager exposes resource-bound Partial APIs inside a Task Container. In AgentDyn tests using qwen3.5-flash, REALM completed 40.0% of 60 clean tasks and 36.4% of 560 injected cases, while reducing the attack success rate from 16.6% to 0.2%.

## Source excerpt

arXiv:2610.39155v1 Announce Type: cross Abstract: Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution toward unrelated resources. Applying least privilege therefore requires identifying the assets needed by a task, including assets whose identities emerge only during execution. We present REALM (Required Execution Assets Linked to a Mission), an approach to identifying and maintaining a task's required assets and their permitted uses. The approach represents required assets as Dependency Graph nodes, resolves prerequisite relationships, and admits newly discovered assets through source-scoped selection. It separates discovering an asset from authorizing its use, while preserving the agent's freedom to choose its computation. The REALM Builder maintains the selected grants and projects Asset Files; the Partial API Manager exposes resource-bound Partial APIs to the Agent inside a Task Container. Across 60 clean tasks and 560 injected cases in AgentDyn, it completes 40.0% and 36.4% of tasks and decreases ASR from 16.6% to 0.2% with qwen3.5-flash as the base model.