Prism reduces tool permissions for AI agents while keeping tasks effective
PRISM: Causal Counterfactual Minimization of Agent Tool Privileges via Information Bottleneck Role Induction
Cryptography and SecurityArtificial IntelligenceMachine Learning
Summary
Large language model agents often get more access to tools than they really need, which can be risky. The authors created PRISM, a method that figures out exactly which tools each agent needs for a task by testing what happens if the tools are removed. PRISM then groups tasks and tools into roles, cutting down unnecessary permissions a lot without hurting success rates. This approach also helps reduce the chances that an agent can cause big problems by limiting its access.
What this means in practice
- •For enterprise security teams: Minimize over-authorization of AI agents accessing internal tools by defining precise roles based on causal necessity.
- •For ai platform developers: Incorporate PRISM to automatically learn and prune tool access roles for LLM agents to improve safety and efficiency.$Commercial implications: Enables safer, role-based access control for AI agents in platforms, a new feature potentially marketable to enterprise clients.
Authors
Yang Luo, Qingni Shen, Tairui Wang, Jiajun Li, Zhonghai Wu
Abstract
This paper shifts the object of role engineering from human users to large language model (LLM) agents, and proposes PRISM to address the over-authorization that arises when an agent obtains full tool privileges through the Model Context Protocol (MCP). PRISM formulates whether a tool is necessary for a task as an intervenable causal proposition, and applies structured interventions in a sandbox to learn a counterfactual necessity model. It then compresses trajectories into discrete latent variables through an information bottleneck, and determines the number of roles from the knee of the rate-distortion curve. Finally, it formalizes pruning as a bilevel Stackelberg game, in which a generative flow network samples diverse near-optimal solutions. On three public benchmarks, AgentDojo, $τ$-bench and ToolEmu, PRISM compresses the number of authorized tools per role by 78.3%, attains a task success rate of 78.2%, reaches a counterfactual necessity accuracy of 88.7%, and lowers the blast radius to 15.9%.