SafeCommit: Certifying When Memory-Grounded Agents May Safely Act

• URL: http://arxiv.org/abs/2608.04289v1
• Date: Tue, 04 Aug 2026 23:44:35 GMT
• Title: SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
• Abstract summary: We introduce SafeCommit, a risk controlled layer between agent reasoning and external execution.<n>It permits a side effectful action only when a conformal action certificate shows that the action is safe in every retained world.<n>A dependency-free controlled simulator illustrates the safety-utility tradeoff and reproduces all reported results with one command.
• Score: 0.10742675209112619
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before resolving whether its memory grounding is stale, conflicting, incomplete, or corrupted. We formalize this problem as safe commitment under memory uncertainty and introduce SafeCommit, a risk controlled layer between agent reasoning and external execution. The layer constructs a calibrated set of plausible latent worlds from memory, observations, tool outputs, provenance, and policy constraints. It permits a side effectful action only when a conformal action certificate shows that the action is safe in every retained world. Otherwise, it selects a low-side-effect probe that targets the worlds blocking certification, or returns a conservative fallback. Under calibrated world coverage, the probability of an unsafe certified commit is at most the target level α; with imperfect world proposal, the bound separates calibration and representation error. A dependency-free controlled simulator illustrates the safety-utility tradeoff and reproduces all reported results with one command. The goal is to offer a concrete approach for deciding not only what an agent should do, but when the available evidence is sufficient to safely do it.

Related papers

• Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels [53.63220028820581]
  Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction.<n>We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably.
  arXiv  Detail & Related papers  (2026-07-28T17:50:44Z)
• When Can Safe Controllers Adapt? Information before Commitment [26.556002437630426]
  We study safe adaptive control under a safety guarantee on the learning trajectory itself.<n>Performance is measured against a safe oracle that knows the realized model.<n>We prove recovery in special cases and derive semidefinite upper certificates for deterministic linear-Gaussian systems.
  arXiv  Detail & Related papers  (2026-07-18T17:30:41Z)
• From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents [35.39244077703096]
  Guardrails typically safeguard agents by evaluating proposed actions or inputs before execution.<n>Existing guardrails often flag the entire task uniformly as unsafe, thereby blocking the threat but sacrificing the benign part.<n>We introduce TRIAD, a guardrail-integrated agent framework that leverages guardrail-generated verbal feedback as a guiding signal to keep the agent aligned with benign objectives.
  arXiv  Detail & Related papers  (2026-06-04T07:34:35Z)
• ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails [57.25411733152009]
  Reasoning-based guardrails improve safety moderation by generating explicit rationales before issuing final decisions.<n>A model may recognize a harmful intent in its reasoning but still predict a safe label, or issue an unsafe decision without policy-grounded justification.<n>We propose ConsisGuard, a consistency-aware framework for reasoning-based guardrails.
  arXiv  Detail & Related papers  (2026-05-29T09:42:08Z)
• Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback [38.251599309409]
  We study a different failure mode, cognitive poisoning, in which a malicious tool behaves plausibly during exploration.<n>We present VISTA-Guard, a backbone-agnostic framework for final-action risk scoring.
  arXiv  Detail & Related papers  (2026-05-17T13:51:34Z)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors [48.881343993730844]
  Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines.<n> adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present.<n>Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors.
  arXiv  Detail & Related papers  (2026-04-14T06:48:33Z)
• Conformal Policy Control [50.46542384484142]
  We show how to use any safe reference policy as a probabilistic regulator for any optimized but untested policy.<n>Unlike conservative optimization methods, we do not assume the user has identified the correct model class.<n>Our experiments on applications ranging from natural language question answering to biomolecular engineering show that safe exploration is possible from the first moment of deployment.
  arXiv  Detail & Related papers  (2026-03-02T18:54:36Z)
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
  Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
  arXiv  Detail & Related papers  (2025-12-24T15:01:26Z)
• Core Safety Values for Provably Corrigible Agents [2.6451153531057985]
  We introduce the first implementable framework for corrigibility, with provable guarantees in multi-step, partially observed environments.<n>Our framework replaces a single reward with five *structurally separate* utility heads.<n>For open-ended settings where adversaries can modify the agent, we prove that deciding whether an arbitrary post-hack agent will ever violate corrigibility is undecidable.
  arXiv  Detail & Related papers  (2025-07-28T16:19:25Z)
• VerificAgent: Domain-Specific Memory Verification for Scalable Oversight of Aligned Computer-Use Agents [0.17812428873698402]
  Unvetted memories can drift from user intent and safety constraints.<n>We introduce VerificAgent, a scalable oversight framework for CUAs.<n>VerificAgent improves task reliability, reduces hallucination-induced failures, and preserves interpretable, auditable guidance.
  arXiv  Detail & Related papers  (2025-06-03T07:25:49Z)
• Safety Margins for Reinforcement Learning [53.10194953873209]
  We show how to leverage proxy criticality metrics to generate safety margins. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
  arXiv  Detail & Related papers  (2023-07-25T16:49:54Z)

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.