Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents

• URL: http://arxiv.org/abs/2606.21856v1
• Date: Sat, 20 Jun 2026 03:24:24 GMT
• Title: Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents
• Abstract summary: We present textbfHarness-MU, the first model-agnostic, zero-tuning infrastructure framework for multi-user LLM agents.<n>Harness-MU achieves the goal of privacy preservation across all access-control attacks, outperforming the standard baseline by 0.28--0.39 in utility score and improving instruction-following accuracy by up to 48.9 percentage points.
• Score: 12.882077862869588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The increasing deployment of large language model (LLM) agents in collaborative workflows demands robust multi-user, multi-principal interaction mechanisms capable of enforcing access permissions, resolving authoritative conflicts, and preventing unauthorized data disclosure. However, a fundamental mismatch exists between the single-user training paradigm of contemporary LLMs and the hard constraints required for multi-principal governance, rendering probabilistic, prompt-based safeguards vulnerable under multi-turn adversarial interactions.Our key insight is that governance constraints -- who is authorized, what is restricted, and whose instructions take precedence -- are deterministic runtime variables that should be enforced by execution hooks rather than entrusted to the LLM. We present \textbf{Harness-MU}, the first model-agnostic, zero-tuning infrastructure framework for multi-user LLM agents. By decoupling language generation from safety orchestration, Harness-MU guarantees unbreakable permission boundaries while maximizing compliant demand satisfaction. Across four frontier open-weight and proprietary models on the \textit{Muses-Bench} benchmark, Harness-MU achieves the goal of privacy preservation across all access-control attacks, outperforming the standard baseline by 0.28--0.39 in utility score and improving instruction-following accuracy by up to 48.9 percentage points. Harness-MU advances the philosophy of \textit{Harness Engineering}, establishing that systematic infrastructure is essential for solving LLM multi-principal governance challenges. The code and data are available at https://github.com/YuanJrShiuan/Harness-MulUser.

Related papers

• Multi-User Large Language Model Agents [18.001343114312853]
  Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making.<n>We present the first systematic study of multi-user LLM agents.
  arXiv  Detail & Related papers  (2026-03-19T19:31:53Z)
• What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models [2.621142288968429]
  Membership Inference Attacks (MIAs) attempt to determine whether a specific data sample was included in a model training/fine-tuning dataset.<n>We propose a novel membership inference approach that captures the token-level probabilities for low-confidence (hard) tokens.<n>Experiments on both domain-specific medical datasets and general-purpose benchmarks demonstrate that HT-MIA consistently outperforms seven state-of-the-art MIA baselines.
  arXiv  Detail & Related papers  (2026-01-27T22:31:10Z)
• A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA [65.38186593873313]
  Multi-Hop Question Answering (MHQA) requires integrating dispersed, interdependent evidence through sequential reasoning under noise.<n>We introduce a proof-of-concept multi-call framework for MHQA, InfoQA.<n>We construct a stringent and noise-rich benchmark to validate our theory and framework.
  arXiv  Detail & Related papers  (2025-09-25T14:11:57Z)
• Enterprise AI Must Enforce Participant-Aware Access Control [9.68210477539956]
  Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data.<n>We show that adversaries can exploit current fine-tuning and RAG architectures to leak sensitive information by leveraging the lack of access control enforcement.<n>We introduce a framework centered on the principle that any content used in training, retrieval, or generation by an LLM is explicitly authorized for emphall users involved in the interaction.
  arXiv  Detail & Related papers  (2025-09-18T04:30:49Z)
• MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments [40.15090158534087]
  We introduce MLA-Trust, the first comprehensive and unified framework that evaluates the MLA trustworthiness across four dimensions: truthfulness, controllability, safety and privacy.<n>We utilize websites and mobile applications as realistic testbeds, designing 34 high-risk interactive tasks and curating rich evaluation datasets.
  arXiv  Detail & Related papers  (2025-06-02T12:56:27Z)
• A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network [53.37983409425452]
  Large Language Models (LLMs) have achieved remarkable success across a wide range of applications.<n>Recently, collaborative frameworks such as the Multi-LLM Network (MultiLLMN) have been introduced.<n>We propose a novel Trusted MultiLLMN framework driven by a weighted Byzantine Fault Tolerance (WBFT) blockchain consensus mechanism.
  arXiv  Detail & Related papers  (2025-05-08T10:04:41Z)
• A Trustworthy Multi-LLM Network: Challenges,Solutions, and A Use Case [59.58213261128626]
  We propose a blockchain-enabled collaborative framework that connects multiple Large Language Models (LLMs) into a Trustworthy Multi-LLM Network (MultiLLMN)<n>This architecture enables the cooperative evaluation and selection of the most reliable and high-quality responses to complex network optimization problems.
  arXiv  Detail & Related papers  (2025-05-06T05:32:46Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)
• Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications [73.58451824894568]
  The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In safety-critical domains, such behaviors could lead to disastrous outcomes. We propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives according to a safety critic.
  arXiv  Detail & Related papers  (2024-02-23T23:22:06Z)
• FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models [79.62191017182518]
  FollowBench is a benchmark for Fine-grained Constraints Following Benchmark for Large Language Models. We introduce a Multi-level mechanism that incrementally adds a single constraint to the initial instruction at each increased level. By evaluating 13 popular LLMs on FollowBench, we highlight the weaknesses of LLMs in instruction following and point towards potential avenues for future work.
  arXiv  Detail & Related papers  (2023-10-31T12:32:38Z)
• Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning [48.667697255912614]
  Mean-field reinforcement learning addresses the policy of a representative agent interacting with the infinite population of identical agents. We propose Safe-M$3$-UCRL, the first model-based mean-field reinforcement learning algorithm that attains safe policies even in the case of unknown transitions. Our algorithm effectively meets the demand in critical areas while ensuring service accessibility in regions with low demand.
  arXiv  Detail & Related papers  (2023-06-29T15:57:07Z)

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.