mlsanityData to 14 Oct 2026

HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution

arXiv 2607.27636 ↗First posted 30 Jul 2026cs.AI cs.RO cs.SEcited by 0

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Recent agentic AI systems may return a heterogeneous response containing notices, requests, handoffs, and actions. Conditions can change before external use, so components from the same response need not remain supported together. Rejecting the whole response discards useful components, whereas checking components independently can leave a dependent without its prerequisite. We present Heterogeneous Admission with Localized Obligations (HALO), a runtime protocol that preserves supported components whose declared prerequisites also remain supported, rechecks each exact action before dispatch, and allows blocked actions to be replaced only by fresh candidates. HALO matched all 96 admission expectations and passed all 20 protocol tests. In structured-response replay, it retained 248/248 supported components, including 128/128 unaffected by unrelated changes, while a whole-response policy retained 0/248. Across ten cold-start PX4/Gazebo sessions, HALO blocked every tested stale route, observed no matching stale setpoint, and completed all fresh recoveries.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 9 of its 21 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

9 of 21 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems9 Jun
  2. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents24 Mar
  3. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandbox25 Sep

Other references · 6

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  3. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  4. 2019Control Barrier Functions: Theory and Applicationscited by 372
  5. 2018SOTER: A Runtime Assurance Framework for Programming Safe Robotics Systemscited by 25
  6. 2026Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflowscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets
  2. 2026Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems
  3. 2026AID-Guard: Stateful Authorization for Delegated Agent Effects
  4. 2026Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents
  5. 2026Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents
  6. 2025HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems
  7. 2026Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift
  8. 2026Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay