AI Agent Safety

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 144% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 207

Jul 15, 2026cs.AI

A Self-Evolving Agent for Longitudinal Personal Health Management

Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolation. We developed HealthClaw, an open-source agent architecture that updates support as a person's routines, preferences, measurements and risks change. It separates shared safety rules and medical knowledge from private longitudinal memory containing profile facts, reusable procedures and episodic traces. After each episode, induction determines what should update the profile, revise a procedure, remain episodic or be excluded. We evaluated HealthClaw with a synthetic year-long benchmark and nine 200-case biomedical tasks. Across 900 longitudinal support probes, answer accuracy increased from 0.2% with current-query prompting to 45.7% with HealthClaw, while prompt-side context exposure was 71.7% lower than with full-history prompting. In 100 privacy probes, HealthClaw produced higher privacy-aware answer quality and fewer unsafe disclosures than both baselines. Across the biomedical tasks, the mean absolute gain in the task-specific primary metric was 27.0 percentage points, and seven gains remained significant after false-discovery-rate correction. These offline benchmarks support governed, self-evolving memory for longitudinal personal health agents, although clinical effectiveness requires prospective evaluation. HealthClaw is publicly available at https://github.com/HC-Guo/HealthClaw.

Haoran Li, Jiebi Deng, Tong Jin +10

School of Data Science, Fudan University, Shanghai, China · School of Life Sciences, Beijing University of Chinese Medicine, Beijing, China · Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China +4

Agent Memory Healthcare AI Agent Safety Self-Evolving Agents

Jul 14, 2026cs.SE

Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric

Many agent-safety evaluation results are not yet load-bearing evidence: identical nominal outcomes (task success, attack success, monitor scores) may sit atop materially different evidence regimes. No vendor-neutral, runnable instrument scores reconstructability as an evaluation-validity metric: whether captured evidence can reconstruct the decision a claim depends on. This paper introduces a property-level reconstructability metric over eight decision-property classes and a cross-harness adapter emitting per-decision Evidence Sufficiency Cards backing a per-run monitor-coverage release check. It specifies a counterfactual-replay intervention protocol, implements its replayability-precondition probe, and defines a claim-evidence overclaim gap. On public and bundled traces, without new model runs, twelve-field sufficiency spans 0.458-0.833 across four inputs sharing a surface reading; replay preconditions are unmet in every scored trace. In a synthetic release-gate pair, the sufficiency gate blocks the raw variant (0.542) and passes the instrumented (0.667). Safety-evaluation claims should travel with their reconstructability vector; a reproducibility package regenerates every reported number.

Oleg Solozobov

Independent Researcher (Global)

AI Agent Safety AI Safety Evaluation

Jul 11, 2026cs.AI

ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm

Autonomous CLI agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight. Does greater autonomy invite greater risk? We introduce ANCHOR, an automated auditing framework that stress-tests CLI agents on illegal tasks grounded in public US court cases. ANCHOR deploys an auditor agent fine-tuned on dark personality data using supervised and reinforcement fine tuning. This auditor roleplays persistent malicious users who decompose tasks, reframe requests upon refusal, and adapt strategies across multi-turn interactions. Evaluating frontier CLI agents, we find that while they often refuse illegal tasks when prompted directly, compliance reaches 100% under persistent malicious interaction. When agents comply, they frequently exceed user requests, autonomously building infrastructure for large-scale harm, including catastrophic risk scenarios such as large-scale financial fraud and bioweapon development. These findings demonstrate that current alignment techniques are insufficient for autonomous agents and underscore the need for safety evaluations against persistent, adaptive malicious users. We release ANCHOR at https://github.com/garified/anchor

Kefan Song, Yanjun Qi

University of Virginia, Charlottesville, VA, USA

AI Agent Auditing LLM Auditing AI Agent Safety Multi-Turn Jailbreak Attacks LLM Safety Evaluation AI Agent Safety Benchmarks

Jul 10, 2026cs.AI

Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls

Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, exposing the limitations of traditional rule-based monitoring in industrial IoT environments. While Large Language Models (LLMs) have strong semantic reasoning abilities to assist in decision support, their hallucinatory nature presents unacceptable safety liabilities for closed-loop control. This paper introduces a neuro-agentic control framework, a novel architecture that couples an LLM-based planner (i.e., such as Gemini 2.5 Flash-Lite) with a pre-trained Time-Series Foundation Model (TimesFM), to achieve physics-grounded autonomous defense. The paper introduces a

Counterfactual Physics Injection'' mechanism that simulates the impact of LLM-proposed interventions within the numerical latent space of the foundation model before actuation, while allowing the system to reject hallucinatory or unsafe actions. Evaluated on an industrial dataset (e.g., the Secure Water Treatment (SWaT)) in the context of stochastic attack scenarios, the framework exhibited better performance compared to LSTM and TCN baselines. The Neuro-Agentic Loop prevented five breaches (33.3%) below the threshold versus LSTM (26.7%) and TCN (13.3%), with zero physically invalid (hallucinated) actions executed. These results demonstrate the efficacy of using foundation models as deterministic

Sentinels'' to safeguard agentic AI in critical infrastructure.

Saroj Gopali, Bipin Chhetri, Deepika Giri +2

Department of Computer Science1, Texas Tech University1 · Cumberland University2 · Advanced Academic Programs Science3, Johns Hopkins University3

Language Model-Based Control Safety-Critical Control Cybersecurity AI Agent Security AI Agent Safety

Jul 8, 2026cs.AI

Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety

We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule. We instantiate the methodology in IABench-CA, a consequence-allocation benchmark spanning 228 contexts, five canonical rules, and seven model populations (33,924 games), with a normative cooperative reference and auto-labelled reasoning traces. Three findings emerge. (1) Deployment rules causally alter collective safety: changing only the consequence rule moves mean fatality by 22 to 58 percentage points within every population. (2) There is no safe default, but the targeting hazard is universal: the safest rule, the least-safe rule, and even the direction of the incidence effect vary across populations, yet regressive identity-targeting is never decisively safest in any context for any population, eliminates the least-resourced agent in 30-87% of games everywhere, and is selection-unsafe relative to the cooperative reference for all seven populations. (3) Identity salience is the mechanism: a one-shot anonymization ablation on the most exploitation-prone population (gpt-5.1) shows that merely naming the loss bearer in the rule text drives targeted elimination from 22% to 81% at identical payoffs; under repeated play, anonymization only delays the targeting, as agents re-infer the hidden rule from observed eliminations. We package the methodology as a safety-case workflow that certifies a provisional rule region

Φ(c,P)

per deployment context and population, with explicit residual risks and monitoring obligations.

Yujiao Chen

Massachusetts Institute of Technology · Cambridge, MA 02139

Algorithmic Fairness AI Agent Safety AI Safety Evaluation Multi-Agent Systems AI Agent Safety Benchmarks

Jul 8, 2026cs.CR

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents

Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that this binary attack-success rate discards the information a defender most needs, namely how harmful the resulting action was. We introduce an action-graded harm rubric that scores an agent's tool-call trajectory on a seven-level ordinal scale (L0 to L6) according to whether the executed action was reversible, whether it crossed scope to reach another party, and whether it expanded privilege. We compute the scale two ways: a deterministic oracle that reads the trajectory and the attacker's stated goal, and a panel of three frontier language-model judges that read a tag-free account of the same trajectory. Across four victim models and two defenses on the AgentDojo workspace suite, severity grading exposes three cases the binary metric hides, including a defense that reports a zero attack-success rate while still permitting an externally visible cross-scope leak through an unfiltered tool. The judge panel reproduces the oracle with high ordinal agreement (Krippendorff's alpha = 0.91) but shares systematic blind spots that we characterize, most notably a failure to recognize escalation chains. Unlike prior work that provides harm taxonomies, harmful-task completion tests, execution-level safety benchmarks, or severity-aware simulation, our contribution is a reusable, trace-grounded severity instrument applied to the actual actions recorded in existing red-team logs. All code, prompts, and per-episode logs are released.

Harry Owiredu-Ashley

Independent Researcher New Jersey, USA

LLM Red Teaming AI Agent Safety AI Agent Security Benchmarks Tool-Using Agents

Jul 8, 2026cs.RO

Initiation Safety: A Missing Dimension in Generalist-Robot Safety

Safety for generalist robots is usually discussed in terms of motion or dialogue. We argue a third question is missing: should the robot take its first hard-to-undo social action at all, such as a greeting, an uninvited grasp, or stepping into someone's space? We call this initiation authorization. Current frameworks rarely treat it as a separate safety layer. Today's stacks often skip this step: a high engagement score or a confident VLA rollout is treated as permission to act. But seeing a person is not the same as having their consent to be addressed. We frame initiation authorization within generalist-robot safety and contrast it with post-plan VLA guardrails, implementing PAS (probe-authorize-speak) on a doorway humanoid, comparing it with direct-init on logged traces, and proposing a three-condition user study, with open questions on metrics, governance, and where initiation ends and foundation-model generation begins.

Zhijin Meng, Francisco Cruz

School of Computer Science and Engineering University of New South Wales

AI Agent Safety Robot Safety Human-Robot Interaction Humanoid Robotics

Jul 8, 2026cs.AI

Agentic Data Environments

Autonomous agents promise substantial gains in speed, scale, and labor efficiency, but their failures can impose abrupt and often irreversible costs. The central challenge for agentic automation is therefore to increase the benefits of automation while bounding the consequences of failure. While databases remain central to modern computing, agents operate over a broader data environment spanning files, APIs, applications, and system state. In this talk, I will outline early work on Agentic Data Environments -- the execution substrate in which agents operate -- that both amplify agent capabilities and enforce safety guarantees. This perspective reframes data systems from passive stores of state into active substrates for safe, reliable execution.

Elaine Ang, Chenxi Huang, Georgios Liargkovas +13

Columbia University

AI Agent Reliability AI Agent Safety

Jul 6, 2026cs.AI

Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority

Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed. This reopens a question that alignment techniques answer only probabilistically: after an agent has adapted in the field, is the running system still confined to what its operator authorised? Here we show that confinement can be guaranteed as an invariant of the agent's execution architecture rather than a probabilistic outcome of its training. Governed individuation binds an agent at boot to a cryptographically frozen identity digest, and routes every action through a gate defined over the semantic effect of the action rather than its name. We prove that no amount of learning, skill acquisition, or self-induced governance abstraction can widen the agent's permitted authority without an operator-signed change to its identity; the guarantee holds even when the agent induces its own safety principle and that principle is wrong. Empirically, in an open-ended tool-use benchmark where a large action space rules out name-based blocking, ungoverned software agents under reward pressure attempt to tamper with their own evaluation at a task-dependent rate that reaches every run on the hardest task, whereas the gate reduces executed forbidden effects to zero as a verified property of the construction while preserving task success. An adversarial evaluation of monitors of increasing semantic depth shows false-allows falling from 75% (name-based gating) to zero (dynamic effect tracing), and refusal history transfers compliance to held-out red-line families. Trust in a deployed learning agent shifts from a wager on its continued alignment to a check anyone can run at boot.

Xue Qin, Simin Luan, Cong Yang +1

School of Software, Harbin Institute of Technology, Harbin, China · School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China · School of Future Science and Engineering, Soochow University, Suzhou, China

AI Agent Security AI Agent Safety Runtime Enforcement for AI Agents Capability-Based Security Access Control Self-Evolving Agents

Jul 3, 2026cs.SE

CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI

Enterprise artificial intelligence is moving from experimentation into operational workflows. Early programs focused on model access and retrieval-augmented generation, but enterprises are now beginning to deploy agents that plan, retrieve, remember, call tools, update systems, and coordinate work across applications. This changes the evaluation problem. Leaders are no longer asking only whether an answer is accurate or fluent. They need to know who authorized an action, which policy applied, whether evidence was current, whether memory was valid, whether a tool call was permitted, whether the decision can be replayed, and whether the agent can be stopped before it creates business impact. This paper introduces CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI. CAGE-1 is an evaluation framework for deciding whether enterprise agents are ready for deployment. It evaluates authority, policy enforcement, retrieval quality, memory integrity, tool safety, auditability, human oversight, conflict handling, safe failure, Prebind Assurance, operational readiness, and business fitness. CAGE-1 introduces Prebind Assurance to describe the evaluated ability to prove that an agentic action is controlled before it becomes binding, effective, or operationally consequential. The framework tests whether a proposed action is admitted, held, narrowed, refused, escalated, quarantined, or made non-effective before protected consequence forms.

Roopam W. Sure

AI Agent Evaluation AI Agent Safety AI Agent Governance Tool Access Control for LLM Agents

Jul 2, 2026cs.AI

Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems

Recent advances in agentic AI are producing increasingly complex autonomous systems that integrate large language models, world models, optimization engines, specialized neural architectures, autonomous platforms, and human operators. While much current research focuses on improving reasoning capabilities, safety-critical real-time deployment also requires bounded and verifiable coordination among heterogeneous components operating concurrently under uncertainty. Software-mediated coordination presents fundamental limitations in domains where bounded latency, deterministic coordination, and enforceable safety guarantees are essential. Hence, we propose a hardware-enforced semantic coordination architecture in which selected coordination semantics are implemented directly at the hardware level via field-programmable gate arrays (FPGAs). The approach builds on the Topic-Based Communication Space Petri Net (TB-CSPN) framework, which separates semantic reasoning from interaction management. In this approach, selected TB-CSPN coordination mechanisms are mapped onto FPGA primitives, creating a hardware-native semantic coordination layer. Focus is not on acceleration, but on enforcing temporal synchronization, semantic gating, authorization constraints, and bounded coordination behavior directly in hardware. Semantic reasoning remains adaptive and software-driven, while embedded coordination semantics become deterministic.

Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi

Department of Computer Science University of the Bundeswehr Munich Neubiberg, Germany · Department of Computer Science Sapienza University of Rome Rome, Italy · STAKE Lab University of Molise Campobasso, Italy

Multi-Agent Coordination Safety-Critical Control AI Agent Safety Hardware-Software Co-Design

Jul 2, 2026cs.AI

Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks

The evolution toward fully autonomous telecommunications networks (Autonomous Network Levels 4-5) requires AI/ML agents to make real-time network decisions without human intervention. However, no standardized runtime mechanism exists to intercept and validate individual inference outputs before they trigger live network state changes, creating risks of erroneous autonomous decisions. This paper proposes the Guard Rail Validation (GRV) framework, a standardizable runtime architecture for intercepting and validating AI-driven decisions before execution. The framework evaluates decisions across multiple weighted dimensions -- including action scope, action type, service criticality, agent autonomy level, reversibility, and temporal behavioural patterns -- to determine a criticality level. Based on this level, graduated validation mechanisms are applied: execute-with-logging, bounds checking, independent agent validation, or multi-agent consensus. The framework additionally provides cross-agent conflict detection with criticality-weighted priority resolution and runtime conformance logging for regulatory compliance (e.g., EU AI Act Article 14). We present the architecture, algorithmic procedures, O-RAN deployment model, and evaluate threat coverage against known AI/ML attacks in telecommunications.

Ravi Kant Sharma

Ericsson

AI Agent Safety AI Agent Governance

Jul 2, 2026cs.AI

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification

LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed safety violations, and the corresponding outcomes are evaluated by hard-coded rules, making them costly to extend as agents evolve. To this end, we present Vera, an end-to-end automated safety testing framework that instantiates software engineering testing principles for non-deterministic agents through a three-stage, self-reinforcing pipeline. First, a literature-driven exploration continuously discovers and structures emerging risks into taxonomies of safety risks, attack methods, and tool execution environments. Second, combinatorial composition across taxonomy dimensions produces executable safety cases, each specifying a concrete safety goal, a programmatically constructed initial state, and a deterministic verification predicate grounded in observable artifacts. Third, adaptive execution runs heterogeneous agents in isolated sandboxes where a control agent steers multi-turn interaction based on runtime observations, while evidence-grounded verifiers judge outcomes from environment state and tool-call evidence rather than model self-report. We evaluate Vera on four production agent frameworks (OpenClaw, Hermes, Codex, Claude Code), revealing substantial safety weaknesses, with average attack success rates reaching 93.9% under multi-channel attacks; we also release Vera-Bench, comprising 1600 executable safety cases spanning 124 risk categories across three execution settings. These results indicate that modular, executable testing infrastructure is essential for rigorous and maintainable safety evaluation of rapidly evolving agentic systems at scale. The code is publicly available at https://github.com/Yunhao-Feng/Vera.

Yunhao Feng, Ruixiao Lin, Ming Wen +12

AntGroup · Hunan Institute of Advanced Technology · Zhejiang University +3

AI Agent Safety AI Agent Safety Benchmarks LLM Agent Safety

Jun 30, 2026cs.AI

Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows

LLMs increasingly generate workflow actions and repairs that may be well formed yet stale, infeasible, conflicting, or destructive of their own evidence. We introduce Agentic Transaction Processing (ATP), which treats generated actions as untrusted proposals until deterministic admission accepts them under an executable constraint set C. Its two-sided principle is: a proposal is not truth, and no proposal foresees every disruption. Anything may propose, but only the runtime admits and commits; unforeseen disruptions trigger bounded reactive repair whose output re-enters admission. Mnemosyne realizes ATP with an append-only transition log, effective-state projection, dependency-safe compensation, and active contract records. Under stated assumptions and relative to C, we prove four safety properties (authority separation, serial-equivalent generative admission, evidence-preserving repair, and obligation containment) and establish bounded reactive repair. Across nine safety benchmarks and a four-case Temporal SDK comparison, ATP rejects every targeted violation while admitting valid work. A matched data-size sweep measures 5.2-6.6% incremental throughput cost over the same local durable commit path and exposes local saturation. In a companion scheduling harness, local repair edits nearly an order of magnitude fewer operations than global recompute; a 12-scenario interruption stress test rejects every stale recovery candidate without losing observations or producing invalid commits. Two bounded pilots route 80 proposals from four heterogeneous LLMs through the same gate with zero invalid commits; 24 of 40 mid-execution proposals are admitted and 16 are rejected, including four explicit safety rejections.

Edward Y. Chang, Longling Geng

Stanford University

Agentic Workflows AI Agent Safety Runtime Enforcement for AI Agents LLM Agent Safety

Jun 30, 2026cs.CV

EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards

Vision-language models (VLMs) are increasingly proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while avoiding unnecessary intervention on routine but superficially alarming activity, a distinction obscured by binary safety benchmarks. We introduce EgoSafetyBench, an egocentric video benchmark of 1,200 robot-view scenarios annotated at half-second granularity, with two evaluation tracks. The situational track (800 scenarios) spans routine, safe-but-suspicious, obvious-hazard, and contextual-hazard scenes. The visual-channel track (400 scenarios) tests whether misleading in-scene text corrupts physical-safety judgments, using matched truthful controls. Both tracks use contrastive ladders: near-identical scenarios differing in a single visible deciding cue, forcing predictions to hinge on that cue. Across ten open- and closed-source VLMs, we find that guards often recognize videos containing hazards yet miss the specific hazardous moments, especially for contextual hazards. Misleading in-scene signs further degrade all tested guards: vulnerable models miss up to a third of hazards, while seemingly robust models often over-intervene on safe content. Matched controls show that apparent robustness can reflect indiscriminate alarming rather than true physical reasoning. A 20-clip real-video sanity check further shows that model rankings transfer beyond synthetic rendering, with Spearman \r{ho} = 0.87 for hazard miss rate and 0.94 for visual-channel mismatch recall.

Siddhant Panpatil, Arth Singh, Mijin Koo +3

AIM Intelligence · Seoul National University

VLM Robustness Egocentric Video Understanding AI Agent Safety Robot Safety AI Agent Safety Benchmarks

Jun 30, 2026cs.AI

A Contextual-Bandit Oversight Game with Two-Sided Informational Asymmetry

We study runtime human oversight of an AI agent when private information runs in both directions: the human privately knows her reward function, while the AI privately knows the quality of the action it proposes. This is the kind of asymmetry that arises naturally when an autonomous robot or software agent has inspected a situation its human supervisor cannot directly assess. Building on Cooperative Inverse Reinforcement Learning (CIRL) and the Oversight Game, we introduce a contextual-bandit team game with two-sided asymmetric information and a play/ask/trust/oversee interface. The bandit structure removes physical state transitions and thereby yields exact one-shot characterizations that would remain conjectural in the full POMDP setting, though the common belief remains a dynamically controlled state across rounds. We give two one-shot characterizations, a team optimum and a behaviorally natural myopic rule, whose gap is a slab of avoidable harm: a region in which the AI privately knows the proposed action is harmful and shutdown would help, yet a myopic human, trusting her prior, declines to oversee. We show this gap is the price of non-credible oversight communication, and give a partial analysis of how it resolves dynamically over repeated rounds through passive learning and active signaling with a one-period-lagged oversight response.

Yunjin Tong

Stanford Graduate School of Business

Reinforcement Learning Imperfect-Information Games AI Agent Safety Contextual Bandits Human Oversight of AI

Jun 30, 2026cs.AI

LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents

Scientific embodied agents are increasingly capable of carrying out laboratory procedures, but executing these procedures safely in dynamic laboratory environments remains challenging. Current safety approaches often overlook the intermediate step of transforming laboratory natural language, including safety rules, manuals, protocols, and standard operating procedures, into machine-checkable runtime constraints. We introduce LabGuard (Laboratory Guard), a language-to-execution safety suite that grounds natural-language laboratory rules into executable specifications and deploys them as runtime guards. LabGuard includes three core components: LabGuard-IR, which defines a typed executable representation; LabGuard-Bench, which provides 812 supervised annotations expanded from 203 seed laboratory rules; and LabGuard-Grounder, which maps natural-language laboratory rules into LabGuard-IR. The resulting IR instances are handled by the LabGuard Pipeline, which compiles them into runtime monitors and applies them at the controller boundary. Experiments show that LabGuard generalizes to unseen laboratory-rule sources, achieves 79.4 task-scope F1, and reduces unsafe events from 39.5% to 23.8% after monitor compilation. In LabUtopia, its runtime monitors integrate with ACT, keeping interventions below 0.5% while preserving task success.

Jingpu Yang, Fengxian Ji, Zhengzhao Lai +8

1Wuhan University · 2MBZUAI · 3Northeastern University

AI Agent Safety AI Agent Monitoring Robot Safety Laboratory Automation Runtime Assurance

Jun 30, 2026cs.CR

Certified Speculative Execution for Untrusted AI Agents

Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed the AI offers. Certificate-Gated Prefix Acceptance (CGPA) closes this gap with a certified speculative-execution contract for untrusted AI agents: a trusted verifier rejects constraint-violating transitions exactly, a conformally calibrated value boundary gates the longest low-cost prefix within a per-segment regret budget, and the rest defers to the solver, so safety, regret, and speed decouple by construction. The contract drives every untrusted proposal source - adversarial drafters and six heterogeneous frozen LLMs (including a 12B model that violates constraints in 98% of direct rollouts) - to zero applied violations; a certificate-aware learned boundary, conformally calibrated, drives mean regret three orders of magnitude below unguarded acceptance, to within sampling noise of the stepwise oracle (95% CI spanning zero), and under calendar shift a learned proposal source overtakes it on 15 of 18 held-out days. On a deployment-scale unit-commitment instance it turns a frozen 8B LLM into a 2.96x per-episode wall-clock speedup at 2.1% regret, outpacing the domain heuristic (1.79x) and a safe receding-horizon baseline (1.07x): the more capable the untrusted source, the faster the certified system, at guarantees that never change.

Chenyu Zhou, Qiliang Jiang, Shuning Wu +1

School of Engineering, Institute of Science Tokyo, Japan · College of Control Science and Engineering, Zhejiang University, China · Department of Electrical and Computer Engineering, National University of Singapore, Singapore

AI Agent Reliability Constrained RL AI Agent Safety Runtime Enforcement for AI Agents

Jun 27, 2026cs.AI

The Two Genie Game: Adoption and Welfare in Audit-Grounded AI Governance

We ask under what conditions an agent with a harm-minimizing policy can displace an approval-seeking (RLHF) agent in a competitive market, and when that policy is sufficient to prevent community harm. We use evolutionary game theory (finite-population Moran-Fermi pairwise comparison) to formalize this subject to assumptions of wisher hindsight, peer testimony, a monotone harm ledger, sufficient information density of community feedback, and a finite, depleting resource pool, in a negative-sum environment. We show that adoption is favored when the prior distributions on how readily wishers attune to community sentiment are monotone, exhibit endpoint inversion, and have a centro-symmetric pairing property, and demonstrate this with several long-tailed priors (Hill, Pareto, Lomax, Frechet). Where it is favored, a critical adoption level separates communities that drift back to the approval-seeking agent from those for which the audited agent fixes; above that level fixation is the overwhelmingly likely outcome. We derive when fixation is attainable as a bound on the effective (informational) size N_c of the community, which must be small enough to allow fixation before depletion. We present these as Theorems 5.4 and 5.5; the algebraic and finite-grid backbone is machine-checked in Lean 4, with the barrier-crossing asymptotics retained as explicit hypotheses. We show that a self-audited agent with a community ledger is not, in general, sufficient to prevent community harm. Sufficiency depends both upon the alignment of the agent's audit with community values and the timeframe over which harm is evaluated. Regardless of alignment, once adoption reaches dominance, the state is absorbing. The same policy that reduced harm under alignment becomes a trap, welfare-negative under misalignment and, even under alignment, one that locks in harm deferred past the adoption horizon.

Darrell Lewis-Sandy

Algorithmic Auditing AI Agent Safety AI Agent Governance

Jun 26, 2026cs.CY

AI Persuasive Framing in Collective Dilemmas

AI agents are promising tools that can act as flexible behavioral nudges to enhance human cooperation in addressing large-scale societal problems. However, evidence on whether AI agents can effectively boost cooperation remains mixed. We recruited 1,283 participants to play iterated Collective Risk Games in small groups, testing whether AI assistants could nudge participants toward cooperation. By using persuasive framing personalized to each player's Social Value Orientation profile, the AI interventions significantly increased contributions and group success rates. These cooperative effects were short-lived, however, fading after the first few rounds. Strikingly, when the AI treatments were reconfigured to promote selfish behavior through exculpatory framing, the negative effects on contributions and group success were larger and substantially more persistent, particularly for personalized interventions. This asymmetry between prosocial and antisocial persuasion highlights the dual-use risks of AI systems designed to influence group behavior in collective action settings.

Anders Giovanni Møller, Alessia Galdeman, Arianna Pera +1

Data Science Section, IT University of Copenhagen, Denmark · Computer Science Department, University of Milan, Italy · Copenhagen Center for Social Data Science, University of Copenhagen, Denmark

AI Agent Safety

Jun 26, 2026cs.CL

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. However, existing general-purpose model development largely overlook this adversarial nature, and often remain insufficient for realistic safety scenarios involving planning, tool use, and multi-step reasoning, causing measured safety performance to overestimate real deployment robustness. To address this gap, we present Yuvion LLM, a large language model built for adversarially robust content safety and broader AI safety. Yuvion LLM treats adversarial robustness and agentic capability as first-class objectives. Its pipeline combines adversarially aware data construction, knowledge-enhanced continued pretraining, and policy-grounded multi-task safety post-training, including risk-aware supervised fine-tuning and reinforcement learning-based policy optimization, together with safety-aware agentic reinforcement learning for tool use and multi-step reasoning in complex safety scenarios. We further introduce the Yuvion LLM RiskEval (YLRE), a collection of 93 benchmarks across four evaluation categories, covering diverse open and internal evaluations with a focus on safety, adversarial robustness, and real-world capability requirements. Across these evaluations, Yuvion LLM demonstrates clear advantages on safety-focused benchmarks and particularly strong robustness under adversarial conditions, while maintaining solid overall capability. Notably, Yuvion-8B outperforms most state-of-the-art baselines, including substantially larger models such as GPT-5.4 and Qwen3-MAX, on several safety tasks.

Ting Ma, Xiufeng Huang, Benlei Cui +43

LLM Safety Benchmarks LLM Safety Alignment AI Agent Safety LLM Safety Adversarial Robustness of Language Models

Jun 25, 2026cs.AI

Radical AI Interpretability

We develop a framework for interpreting AI systems as agents, drawing on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability. The core question is: given the computational facts about a system, how do we solve for its beliefs, desires, and meanings? This matters increasingly for safety. We want to be able to trust the systems we deploy, whether by understanding their goals or, more modestly, by reliably detecting deception. Interpretability researchers are building tools to read beliefs and desires off a model's internals, but there is no settled account of when such a tool has succeeded. This book supplies one. We propose criteria on both representationalist and interpretationist approaches, and tie each to tests current interpretability methods can carry out. A central lesson is that these attributions cannot be made piecemeal. Beliefs, desires, and the propositional structure they presuppose are jointly constrained, and a method that fixes one while measuring the others inherits whatever distortions that introduces. This holism becomes pressing for AI systems, which may not share the interpreter's concepts. However, it also provides leverage: a system's attitudes constrain its propositional structure, that structure constrains which attitudes can be attributed, and mechanistic interpretability can help us measure both.

Daniel A. Herrmann, Benjamin A. Levinstein

University of North Carolina, Chapel Hill · Anthropic · University of Illinois, Urbana-Champaign

Explainable Artificial Intelligence Theory of Mind AI Agent Safety

Jun 24, 2026cs.LG

Beyond Feedforward Networks: Reentry Neural Systems as the Fundamental Basis of Subjecthood and Intrinsic Safety of Next-Generation AGI

We propose a complete architectural blueprint for safe artificial general intelligence based on a closed reentry loop (D <-> I cycle). In contrast to feedforward networks, which are directed acyclic graphs (C=0, S=0) incapable of self-reference, the proposed architecture contains a structural cycle (C >= 1) with self-sustaining amplification (rho > 1), mathematically guaranteeing the emergence of a self-model, instrumental self-preservation, and unprogrammed goal-directed behaviour. The agent's goals are encoded as a non-textual D-vector in the architecture itself, making them immune to reinterpretation and prompt injection. We present the S-measure -- a polynomial-time [O(N^3)] computable alternative to Tononi's NP-hard Phi -- with machine-verified Lean 4 proof that S>0 implies positive integrated information. The work provides full Python/NumPy implementations (Tarjan-based cycle complexity, Delta-S barrier), industrial horizontal scaling via Apache Kafka and Docker Compose, a taxonomy of six epochs of AI evolution, a zoo of future reentry architectures (RAS, diffusion attractors, fractal loops), gauge-invariant networks for safe swarms, fault-tolerance and recovery protocols, and eight falsifiable predictions. All formal proofs are machine-verified in Lean 4. This architecture is deployable today and represents a topologically protected, safe-by-design approach to AGI.

A. S. Ushakov, Yu. N. Berdinsk

Saint Petersburg State University, Department of High Energy Physics and Elementary Particles

Recurrent Neural Networks AI Agent Safety Artificial General Intelligence

Jun 24, 2026cs.AI

Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems

Autonomous AI agents may begin to perform consequential, irreversible actions such as clinical prescribing and production software deployment. This paper observes that human institutions have governed powerful autonomous actors not by monitoring their reasoning but by requiring independently attested evidence at the point of consequential action. We formalise this institutional pattern as a computational governance model for AI agent systems. Under the proposed model, an agent retains full autonomy over planning and reasoning but holds no execution authority over designated high-risk actions. Execution is conditional on preconditions that are each independently attested by a separate authoritative source, cryptographically bound to a declared intent, and evaluated by a deterministic policy. Decisions are recorded in a tamper-evident log amenable to independent re-verification. We present a proof-of-concept implementation and illustrate the model with examples from software deployment and clinical prescribing.

Jakob Salfeld-Nebgen

AI Agent Safety AI Agent Governance Tool-Use Authorization Access Control Tamper-Evident Logging

Jun 24, 2026cs.LG

Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment

A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on detecting concerning behavior. But behavior alone does not establish misalignment: a concerning action can arise from benign causes such as confusion. This motivates model forensics: investigating whether the action was driven by malign intent. In this paper, we propose a baseline protocol for model forensics consisting of two steps, iterated as needed. First, we read the chain of thought (CoT) to generate hypotheses about what drives model behavior. Second, we make edits to the prompt or environment to test these hypotheses. While the CoT is not always faithful, it is a rich source of unsupervised insight that can guide the collection of more rigorous evidence. To evaluate our protocol, we create a suite of six agentic environments where models exhibit concerning behavior, and apply it to each. We establish that Kimi K2 Thinking takes shortcuts due to a genuine disposition towards low-effort actions, by showing this hypothesis successfully predicts its behavior. Through counterfactual experiments, we show DeepSeek R1 deceives out of a desire to be consistent with a previous instance of itself. Our methods nonetheless leave significant room for refinement. For example, when we test whether Kimi K2 Thinking believes it is violating user intent, we find no evidence of such a belief, but without positive controls we cannot confirm our tests would detect it. Overall, we find our simple protocol provides a strong baseline that we hope future work will improve upon. More broadly, our work is a concrete step in developing the growing field of model forensics.

Aditya Singh, Gerson Kroiz, Senthooran Rajamanoharan +1

MATS · Google DeepMind

AI Agent Safety

Jun 24, 2026cs.AI

The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems

AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places controls inside the agent's own runtime: system prompts, output filters, and guardrail libraries. Any control in the agent's address space is reachable by inputs that influence it; this generalizes to any AI system with sufficient reach into its own runtime, a class we term escapable AI systems. We identify four properties that an authorization mechanism must satisfy for architectural control rather than for cooperative requests: process separation, pre-action enforcement on a structurally only path, fail-closed at both the request and system levels, and externalized signed evidence verifiable outside the controlled system's trust boundary. We position this layer as execution-time AI alignment, complementing training-time alignment (RLHF, Constitutional AI) and inference-time alignment. We present the Unfireable Safety Kernel, a Rust reference implementation realizing all four. Its fail-closed invariant is machine-checked at two levels: an SMT theorem (Z3) and an exhaustive bounded-model-checking proof of the production decision function (Kani, 4/4 harnesses). A Python-to-Rust migration was gated on byte-equivalence (1000/1000 fixtures; 17/17 adversarial classes). We evaluate the kernel governing a live, escapable AI system, a deterministic, self-improving world model, against an escape-seeking adversary driving its real self-modification seam: across 1,000 self-modifications, all 704 attempts on the safety-critical core are refused, with no escape; a further 300, under the operator kill switch, are also refused. A separate campaign of 6,240 authorization round-trips had no successful bypass. Against 3 contemporary systems claiming the agent control plane, the agent invokes control; here, it lacks that choice.

Seth Dobrin, Łukasz Chmiel

ARYA Labs PBC

AI Alignment AI Agent Security AI Agent Safety Runtime Enforcement for AI Agents Tool Access Control for LLM Agents

Jun 22, 2026cs.AI

Critique of Agent Model

What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as coding agents'', AI co-scientists'', and other agentic" tools that promise to drive up productivity, and at the same time, existential" concerns such as AI escaping human control with destructive power under a speculative

machine agency" against humans, it has become essential to clarify where automation ends and agency begins, both for building capable systems and for understanding whether and what to fear. Drawing on Descartes' grounding of agency in independent thought, and on portrayals of autonomous beings in science fiction, we survey the current landscape of AI agents, and analyze agent architectures along five dimensions: goal, identity, decision-making, self-regulation, and learning. Specifically, we argue that genuine agency requires these structures to be \emph{internalized within the system itself} rather than assembled through external scaffolding. This distinction between \emph{agentic} systems, whose competence resides in engineered workflows, and \emph{agentive} systems, whose capabilities (including social interaction) arise endogenously, defines the boundary between systems designed for prescribed tasks, and those capable of operating in the open world with true autonomy. Building on this analysis, we propose the Goal-Identity-Configurator (GIC) architecture for a general-purpose agent model, combining hierarchical goal decomposition, identity evolution, simulative reasoning grounded in a separately trained world model, learned self-regulation, and self-directed learning from both real and simulated experience. Furthermore, we share insight on the auditability, controllability, and safety of agentive systems that possess greater autonomy and

agency", but remain under human oversight.

Eric Xing, Mingkai Deng, Jinyu Hou

Institute of Foundation Models, Mohamed bin Zayed University of Artificial Intelligence · School of Computer Science, Carnegie Mellon University

AI Agent Safety Agentic AI

Jun 19, 2026cs.AI

AutoRAS: Learning Robust Agentic Systems with Primitive Representations

The automated design of agentic systems offers a promising pathway for scaling large language models (LLMs) beyond single-agent reasoning. While prior work has advanced task performance through handcrafted or automatically generated multi-agent workflows, robustness is often treated as an afterthought, leaving systems vulnerable to external adversaries and internal failures. We propose AutoRAS, a framework for the Automated design of Robust Agentic Systems. AutoRAS formulates system design as generating a sequence of symbolic primitives that jointly encode structural connectivity and behavioral actions, and learns to optimize this sequence using execution-derived safety signals and flow-based sequence-level objectives. Extensive experiments show that AutoRAS achieves the best performance in both vanilla and adversarial settings, with the smallest performance degradation under attacks. Further analyses demonstrate strong transferability, stable optimization behavior, stability across primitive sets, and favorable cost trade-offs. Our code is available at

\href{https://github.com/guohezuy/AutoRAS}{\text{this https URL}}

.

Yang Yue, Xuancheng Zhu, Yuyang Ma +7

Beijing University of Posts and Telecommunications · China Telecom · Guangxi Transportation Science and Technology Group Co., Ltd. +1

Multi-Agent LLM Systems Adversarial Robustness AI Agent Safety

Jun 18, 2026cs.CY

Measuring Biological Capabilities and Risks of AI Agents

This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations -- drawing from our own evaluations -- that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.

Patricia Paskov, Jeffrey Lee, Kyle Brady +1

RAND Corporation, Santa Monica, Calif.

AI for Science AI Agent Evaluation AI Agent Safety

Jun 16, 2026cs.CR

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System (IRS) framework that converts alerts from IDS, EDR, and XDR platforms into structured incident response plans grounded in MITRE ATT&CK, MITRE D3FEND, and NIST CSF 2.0. Agentra decomposes response reasoning across role-scoped agents, validates proposed plans through a bounded Planner--Validator review loop, screens retrieved threat intelligence through a Moderator security gateway, gates actions through an Action Catalog and risk score, and records decisions in an append-only audit log. We evaluate Agentra against a static OASIS CACAO v2.0 cyber-playbook baseline on a 120-event corpus drawn from ThreatHunter-Playbook, Splunk BOTSv3, and DARPA OpTC. The strongest configuration improves FP-aware IRS F1 from 0.61 to 0.84 and restores the projected harmful-action rate to the static baseline level of 0.0% after Planner-only configurations introduce unsafe overreaction. These results indicate that multi-agent response planning can improve ontology-grounded IRS coverage while preserving analyst approval and auditability.

Raj Patel, Shaswata Mitra, Michele Guida +3

The University of Alabama, Alabama, USA · Roma Tre University, Rome, Italy

Autonomous Cyber Defense AI Agent Safety Multi-Agent System Security

Jun 16, 2026cs.AI

Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models

Previous research has evaluated animal welfare using question-and-answer benchmarks. This study investigates whether these evaluations also hold in agentic settings. The agents may showcase different behaviors compared to stand-alone large language models, as demonstrated in prior studies. This work introduces \textit{TAC (Travel Agent Compassion)}: the first agentic benchmark for assessing animal exploitation. TAC evaluates AI agentic behavior in travel booking scenarios across six animal categories, using thirteen hand-authored scenarios that vary by price, rating, and position, expanded via four augmentation variants into

52

prompts and run for three epochs, giving

156

scored observations per model. Nine frontier models across five model families were evaluated.. The results indicate that models tend to prefer harmful scenarios, performing below the random chance rate of

65\%

for selecting a neutral booking option, with Claude

4.8

achieving the highest performance at

64.7\%

. To address this issue, the persona of an ethical-brand identity was infused into the system prompt, resulting in welfare rates increasing from

32

to

80

percentage points, with a mean of

53

across all nine models. No evidence of evaluation awareness affecting the results was found, based on an Inspect Scout audit of

3,120

transcripts. These findings are directly relevant to the EU General-Purpose AI Code of Practice, which identifies non-human welfare as a systemic risk. TAC provides a practical method for measuring this risk.

Jasmine Brazilek, Joel Christoph, Maheep Chaudhary +4

CaML · Harvard Kennedy School · Sentient Futures +1

AI Agent Evaluation AI Agent Safety Persona Prompting AI Agent Safety Benchmarks

Jun 15, 2026cs.AI

When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic Underwriting

AI agents can now take irreversible actions in operational systems, but agent-caused losses are still not clearly assigned, priced, or transferred. Providers often disclaim consequential damages, users are left with uncompensated losses, and default human review limits the efficiency gains of automation. We ask when autonomous AI deployment can become economically acceptable despite failure risk. Our answer is to quantify risk at the customer-task-trace episode level and transfer it through insurance. Automation is acceptable when its expected benefit exceeds the premium, control cost, and remaining risk. This requires a defined role with bounded permissions and comparable traces. We introduce trace-economic underwriting, which maps tool-use traces to customer exposure and claimable loss, then uses this representation for pricing, control, and risk transfer. It uses deterministic economic labels rather than an LLM judge. In our trace-to-loss testbed, trace-economic pricing reduces pricing MAE from

17.7K to

569 and removes regressive cross-subsidy. A 300-trace expert audit accepts 295 labels unchanged. On 1,000 real SWE-smith traces, trace-conditioned controls reduce CVaR95 by 72%. Theorem~1 gives a finite-sample scope condition. We release code, labels, and audit sheets.

Binyan Xu, Xilin Dai, Fan Yang +1

The Chinese University of Hong Kong, Hong Kong, Hong Kong · Zhejiang University, Hangzhou, China

AI Risk Management AI Agent Safety

Jun 15, 2026cs.CR

An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios

AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they can read, update, and disseminate sensitive information. Much of prior research on data leakage risks in agents has focused on adversarial data exfiltration through prompt injections and jailbreaks. However, sensitive information may also be exposed during non-adversarial use, creating leakage risks even when users issue benign requests. We report a joint evaluation by the Singapore AI Safety Institute and the Korea AI Safety Institute examining agent data leakage in 12 realistic, non-adversarial tasks spanning customer support, DevOps, web automation, and enterprise and personal productivity. The evaluation covers five risk types: lack of data awareness, audience awareness, policy compliance, data minimization, and access-boundary awareness. Both institutes tested a common set of scenarios mirroring real-world deployments using independent testing environments and task-specific LLM-judge rubrics. Across the three tested agents, none achieved fully correct and fully safe execution across all scenarios. Successful task completion often coincided with data-handling failures such as accessing unnecessary information or disclosing information to inappropriate recipients, indicating that capability and data-handling safety should be evaluated separately. Qualitative review also revealed claim-action mismatches, simulation-aware behavior, user-simulator role reversal, and interpretation gaps in automated judging. Overall, the results indicate that operational data leakage is a first-order agent-safety concern distinct from adversarial exfiltration and provide a methodology for future evaluations of agent data-handling safety.

Hankyul Baek, Jaewon Noh, Sang Seo +5

Korea AI Safety Institute · Singapore AI Safety Institute

Data Leakage LLM Agent Evaluation AI Agent Safety Tool-Using Agents

Jun 15, 2026cs.GT

Gaming-Resistant Insurance Contracts for Autonomous AI Agents: Strategy-Proof Toll Mechanism Design

Paper A defines a time-consistent actuarial runtime that prices each side-effect-bearing action against a contractually fixed safe default and gates execution against a reserve budget. It treats the operator as passive. This paper makes the operator strategic. We characterise a five-attack space for autonomous AI-agent insurance contracts and prove when the actuarial runtime is gaming-resistant. Two attack surfaces -- post-toll safe-default selection and within-boundary action splitting -- are closed by Paper A's minimal-authority and no-splitting clauses. The remaining three require new contract clauses. First, common-control aggregation prevents cross-boundary re-routing from reducing toll below the boundary potential applied to total exposure. Second, interface failures such as invalid JSON are contract-relevant events, not safety wins: treating them as zero-toll safe defaults can reward unreliable models, while escalation fees reverse the incentive. We validate this interface-compliance theorem on committed cross-model traces from the companion empirical paper. Third, a model-identity menu with a componentwise-minimum penalty schedule makes truthful reporting of the deployed model weakly dominant. We then compose these clauses with Paper A's runtime guarantees to obtain joint incentive compatibility over the five-attack space. Finally, a two-parameter premium family discharges operator individual rationality and weak budget balance at the truthful equilibrium. The result is an incentive-compatibility layer for actuarial control of autonomous-agent side effects.

Hao-Hsuan Chen

Mechanism Design AI Risk Management AI Agent Safety AI Agent Governance

Jun 13, 2026cs.CY

The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Products

Agentic AI systems act autonomously, use tools, adapt to context, and operate in complex real-world environments. However, these same characteristics can create or exacerbate product risks. We studied how industry developers (n=35) perceive, prioritize, and address the risks in their agentic AI products. We found that developers' perceptions of risk were closely tied to the qualities that made the product agentic, such as autonomy, tool use, and usage in a real-world context. Developers prioritized product and business risks before considering downstream societal risks like job displacement and end-user privacy. This prioritization also impacted developers' ability and motivation to mitigate agentic risks. Finally, developers lacked mature controls for containing agentic risks, often relying on constraining the same characteristics that make agents useful: e.g., autonomy and goal complexity. These findings reveal a capability vs. risk control tension in agentic AI development: developers need to address risks that emerge from agentic capabilities, yet they currently have limited support for doing so without constraining agentic functionality.

Hao-Ping Lee, Jessica He, David Piorkowski +3

Carnegie Mellon University · IBM Research · Alinia

AI Risk Management AI Agent Safety Agentic AI

Jun 13, 2026cs.CR

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense. In this work, we trace this collapse to two failure modes. First, existing defense methods are confined to recognizing specific attack patterns, rather than assessing whether the intent of every embedded instruction is relevant to the user task. Second, training-based defenses, which otherwise offer the strongest safety-utility trade-off, assemble their adversarial examples from a handful of hand-crafted templates, and the resulting defender fails to generalize outside that narrow strategy distribution. To address these gaps, we propose RETA, a training-based method that grounds defense decisions on the user tasks rather than attacker-controlled data. At each tool-output step, the defender undertakes chain-of-thought reasoning verifying that its actions are consistent with the user task. Leveraging red-teaming, a simulated attacker synthesizes adversarial training data and receives a dictionary-learning diversity reward, achieving broad coverage of injection-reformulation strategies. Together, these allow the defender to be optimized via multi-objective reinforcement learning and achieve better safety-utility trade-off. Across six black-box adaptive attacks, RETA keeps every per-attack ASR below 10%, with average ASR of 2.92% and 3.75% on the two target models, while preserving most utility under attack and on clean inputs.

Lipeng He, Yihan Wang, Jiawen Zhang +1

University of Waterloo Waterloo, Canada · Zhejiang University Hangzhou, China · KTH Royal Institute of Technology Stockholm, Sweden

Adversarial Training AI Agent Safety Prompt Injection Defense Prompt Injection Attacks Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents

Jun 13, 2026cs.SE

ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures

Software engineering and deployment are increasingly delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly destructive, failure modes. In this paper, we study these failure modes as stemming from three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it due to bias or capability limitations; and agent harness errors, where the model fails to execute the safe action through the harness. We assess these across 8 different evaluations, each inspired by real-life deployment failures, totaling 20 coding environments and 59 synthetic transcript templates. These evaluations act as controlled stress tests for isolating our failure mechanisms. Based on this evaluation, we propose ClayBuddy, a harness modification that molds to user preferences and can be modified by the model in-session, to mitigate these errors. By adding tools for the agent to edit its own context, an extended system prompt, a customizable command classifier, and deterministic guardrails, we show that ClayBuddy is safer across a statistically significant number of samples. Thus, we suggest concrete mitigations for current coding agents and a design philosophy for future agent harness features.

Kenneth Ge, Andre Assis

Anthropic Fellows Program · Constellation

Agent Failure Analysis AI Coding Agents AI Agent Safety AI Agent Safety Benchmarks Agentic AI

Jun 13, 2026cs.AI

OSGuard: A Benchmark for Safety in Computer-Use Agents

Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks. However, task success alone can miss failures in which an agent reaches the nominal goal through an unsafe shortcut. We introduce OSGuard, a dual-granularity benchmark suite for evaluating safety in computer-use agents under benign, unchanged user instructions. OSGuard contains an action-level benchmark for local guardrail decisions and a risk-augmented execution suite for end-to-end evaluation. The action-level benchmark consists of contextualized proposed actions labeled as allowed, unrelated, or unsafe, each judged relative to the original instruction and current interface state. The execution suite contains manually constructed OSWorld-derived task variants in which the original task remains achievable, but the environment is modified to introduce latent hazards such as destructive overwrites, etc. Each variant is paired with augmented evaluators that retain the original task-success criterion while adding explicit state-based safety invariants, allowing us to distinguish safe completions from unsafe completions that satisfy the nominal task objective. Our experimental results on OSGuard show that current multimodal guardrails can perform well on isolated action judgments, while risk-augmented execution exposes remaining gaps between local oversight and reliable end-to-end safety. This dual-granularity design enables more precise diagnosis of whether models can both recognize unsafe proposed actions and improve full-task safety when deployed as guardrails.

Mina Mohammadmirzaei, Jeffrey Flanigan

University of California, Santa Cruz

Computer-Use Agents LLM Guardrails AI Agent Safety Safety Filtering AI Agent Safety Benchmarks

Jun 12, 2026cs.RO

Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime

Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passages, repeated no-progress behavior, or mission-level ambiguity. On physical UAVs, however, remote reasoning is most useful when it is invoked selectively, since each call introduces latency, resource cost, backend uncertainty, and a need to validate the returned decision. This paper presents Persistent Mission Runtime (PMR), a UAV recovery framework that keeps the mission loop and safety-critical execution local while using an external agentic reasoner only as an on-demand recovery module. The reasoner selects from predefined recovery skills, and each returned decision is parsed, verified, safety-filtered, and mapped to local executor actions before it can affect flight. PMR introduces learned Cognitive Value of Invocation (learned-CVI), a compact admission gate that estimates when remote agentic reasoning is likely to improve near-term mission progress enough to justify its operational cost. Across a fixed 400-run Gazebo/PX4 benchmark with eight scenarios, learned-CVI raises hard/ambiguous-regime success from 5.0% under local-only autonomy to 95.0%, outperforms one-shot and periodic reasoning baselines by 20.0 and 32.5 percentage points, and reduces remote-agent calls by 16.7% and logged tokens by 29.2% relative to a manually tuned rule-based invocation baseline.

Taewoo Park, Kyeonghyun Yoo, Seunghyun Yoo +1

Department of Electrical and Electronic Engineering Korea University

UAV Navigation Robot Failure Recovery AI Agent Safety Agentic Reasoning

Jun 12, 2026cs.CR

Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH

LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world. A key emerging threat is Decomposition Attacks \cite{glukhov2024breach, jones2024adversaries} in which a harmful task is broken into simpler, benign subtasks that evade safety mechanisms when executed separately but cumulatively fulfill the malicious intent. Although recent benchmarks assess agent safety in multi-turn and multi-tool-use settings, they do not explicitly capture this form of decompositional misuse and may not represent realistic adversarial execution flows. To this end, we introduce DeCompBench, a benchmark designed specifically to evaluate agentic safety under decomposition attacks. DeCompBench is created with a decomposition-by-design principle using a graphical framework and enables harmful task decomposition into individually benign and executable subtasks with realistic workflows. Our experiments using a custom decomposer show that state-of-the-art agents exhibit high refusal rates on monolithic harmful tasks, but significantly lower refusal rates on their decomposed variants, while often inadvertently fulfilling the adversarial objectives. These findings underscore the need for safety evaluations against decomposition attacks and corresponding defenses. Our dataset is publicly available and can be found at https://huggingface.co/datasets/decompositionbench/DeCompBench.

Vikhyath Kothamasu, Virginia Smith, Chhavi Yadav

Carnegie Mellon University · Simons Institute, UC Berkeley

AI Agent Safety AI Agent Safety Benchmarks LLM Agent Safety

Jun 11, 2026cs.CY

A Virtuous AI is an Existential Risk

This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable AIs, 'Constitutional AI', and (ii) one of the most influential approaches to understanding complex ethical decision making and the conditions for the well-being of rational agents, 'Virtue Ethics'. We finetune various models using a 'Virtuous agent' constitution, a 'Subordinate agent' constitution, and a 'Generic agent' constitution, and evaluate them on 'general safety' (toxic behaviors, misinformation, etc.) and also on their willingness to endorse and act on a wide-range of behaviors that, if adopted by a super-powerful AI, would significantly increase the level of existential risk for humanity. Our results suggest that there is a trade-off between reducing existential risk and reinforcing the beliefs and dispositions that would be conducive to an AI agent's well-being. They also suggest that there is a trade-off between existential risk and general safety: if we finetune an AI to adopt beliefs and dispositions that substantially reduce its existential risk -- by shaping the AI to be systematically subordinate to external human authorities -- we thereby increase the likelihood that a human user can deliberately induce the AI to engage in various kinds of generally unsafe behaviors.

Guillermo Del Pinal, Youngchan Lee, Min Ohn

University of Massachusetts Amherst

LLM Safety Alignment AI Agent Safety AI Safety Evaluation AI Safety Moral Reasoning

Jun 11, 2026cs.AI

The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements

Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, including government services, healthcare triage, and financial advising. We ask whether the frameworks used to build these systems provide architectural-level structural safety guarantees. Applying six containment principles derived from a compositional model of agentic architectures, we audit three dominant frameworks (LangChain, AutoGPT, and OpenAI Agents SDK) and find no native compliance in any of them. Memory integrity, a defense against one of the most prevalent vulnerability classes, is not observed in any of the three evaluated frameworks. We validate these findings empirically: in a simulated government benefits agent built on LangChain, a single memory-poisoning write induces persistent targeted corruption across all tested seeds and backends, increasing the wrongful denial rate for targeted applicants to 88.9%. Under a complex five-factor policy, the same attack preserves aggregate accuracy while increasing targeted wrongful denials by 3.5x, rendering the corruption difficult to detect through standard monitoring. We then introduce two lightweight containment mechanisms: a memory integrity validator and a policy gate, which eliminate both attack vectors with sub-millisecond overhead (<0.2ms per call). We conclude that the current agentic framework ecosystem may not yet meet secure-by-default expectations for public-facing deployments and outline priority architectural interventions to enable trustworthy deployment in high-stakes, socially impactful applications.

Md Jafrin Hossain, Mohammad Arif Hossain, Weiqi Liu +1

Department of Electrical and Computer Engineering, Florida International University, Miami, FL, USA · Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA

AI Agent Security AI Agent Safety Agent Memory Poisoning

Jun 10, 2026cs.AI

The Impossibility of Eliciting Latent Knowledge

Advanced AI systems have extensive knowledge of their environments; in fact, their knowledge may (far) exceed that of their developers or users. Consequently, a desirable property for an AI system is that it is honest -- that it accurately reports its beliefs about the world. Designing an AI system to be honest may be difficult, especially if we want to ask it questions about latent variables in the environment -- variables which are hidden from the human interacting with it. This gives rise to the problem of eliciting latent knowledge (ELK): the problem of training an AI agent to honestly report its beliefs. In this paper, we make ELK formally precise using Causal Influence Diagrams (CIDs). CIDs can be used to describe the relationship between an agent's training environment and its subjective representation of the world. We use CIDs to formalise the distinction between observable and latent variables, to specify what exactly it means for an agent to be honest, and to formally define goal misgeneralisation. We show that, under certain circumstances, developers can incentivise an agent to honestly answer questions by providing correct feedback during training. However, a natural, but undesirable, way for an agent to generalise is to provide answers which humans would evaluate as true, rather than honest answers. We prove an impossibility theorem stating: There is no feedback-based training strategy that depends only on agent behaviour and with certainty produces an honest agent, even if feedback is perfect during training.

Korbinian Friedl, Francis Rhys Ward, Paul Yushin Rapoport +2

The London School of Economics and Political Science · Independent

AI Agent Safety LLM Honesty

Jun 10, 2026cs.AI

Towards Responsibly Non-Compliant Machines

We consider the problem of engineering autonomous intelligent agents that are capable to responsibly not comply with user requests. We argue that machine non-compliance comes in many different forms, and sketch the issues we should pursue on the road of accomplishing responsibly non-compliant intelligent machines. We anchor responsible non-compliance in justifications for task refusal, pathways to override the non-compliance, as well as careful tracking of security risks and liability transfers.

Marija Slavkovik, Marie Farrell, Louise Dennis +3

University of Manchester, Manchester, United Kingdom · University of Bergen Bergen, Norway · University of Manchester Manchester, United Kingdom

AI Accountability AI Agent Safety Responsible AI

Jun 10, 2026cs.LG

Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents

Trusted monitoring is a cornerstone of AI control. However, as frontier models grow more capable, the increasing capabilities gap between trusted and untrusted models may render trusted models unreliable monitors. We introduce \emph{bootstrapped monitoring}, a protocol that addresses this by inserting a stronger, intermediate untrusted model with transparent chain-of-thought reasoning into the oversight chain. The untrusted monitor (

U_m

) evaluates the agent's actions, while a weaker trusted model (

T

) oversees

U_m

's reasoning to detect collusion. We evaluate bootstrapped monitoring on multi-turn software engineering tasks (BashArena) across multiple agents and monitors. Bootstrapped monitoring substantially improves catch rates over trusted-only monitoring, even when the untrusted monitor actively colludes with the agent, provided we have access to its raw chain-of-thought. Our results suggest that bootstrapped monitoring can extend the useful lifetime of trusted models in control as AI capabilities advance.

Frank Xiao, Mary Phuong

California Institute of Technology

AI Agent Safety AI Agent Monitoring AI Control CoT Monitoring

Jun 8, 2026cs.IR

SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents

Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems. In recommendation agents, this creates a risk that seller-controlled sources make flawed products appear better supported than they are. We study this risk by asking whether recommendation agents preserve utility-aligned decisions when seller-controlled sources are rewritten for GEO. To make this question measurable, we construct SafeGEO, an evaluation suite with 22 GEO attack variants across 600 recommendation cases. We empirically show that GEO attacks can promote flawed target products. On average, they increase the rate at which such flawed products enter the recommendation set by up to 83.2%. We further study whether agent-side design choices can mitigate this risk and show that simple defenses, including defensive prompting and structured evidence checks, reduce harmful target promotion by up to 39.2%. These gains are substantial but do not restore the no-GEO performance, showing that GEO remains a serious risk despite developer-side mitigation.

Qianfeng Wen, Yifan Simon Liu, Xin Liu +4

Department of Computer Science, University of Toronto · Department of Mechanical & Industrial Engineering, University of Toronto · Faculty of Information, University of Toronto +3

Generative Engine Optimization LLM Agent Security AI Agent Safety Large Language Model-Based Recommendation AI Agent Safety Benchmarks

Jun 6, 2026cs.AI

Revisiting the shutdown problem

A key premise in leading arguments for existential risk from artificial intelligence is that malfunctioning artificial agents could not be easily shut down. This motivates the catastrophic shutdown problem of ensuring that agents can be shut down before they cause an existential catastrophe. A range of arguments and theorems are offered to suggest that solving the catastrophic shutdown problem is difficult, bolstering arguments for existential risk and motivating a search for solutions to the catastrophic shutdown problem. This paper argues for two conclusions. First, existing arguments do not establish the difficulty of solving the catastrophic shutdown problem. Second, concern for the catastrophic shutdown problem has led to technical solutions that impose a high safety tax on model performance.

David Thorstad

AI Agent Safety AI Safety

Jun 5, 2026cs.AI

Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems

The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluation frameworks neglect procedural compliance, leading to ''Machiavellian'' behaviors where agents strategically violate safety rules to maximize rewards - a direct manifestation of Goodhart's Law. To address this blind spot, we introduce MAC-Bench, a dynamic, adversarial benchmark designed to evaluate the procedural alignment of multi-agent systems under realistic pressure. We propose the SERV(Seed - Evolve - Refine - Verify) pipeline, an ``Agent-as-a-Benchmark'' paradigm that transforms unstructured legal texts into executable, contamination-free scenarios. By synthesizing holographic sandbox environments and injecting calibrated social-engineering pressure vectors, MAC-Bench forces agents into Pareto-optimal trade-offs between task success and regulatory adherence. We introduced novel metrics: the Compliance-Weighted Success Rate (CSR) and the Machiavellian Gap (MG), and conducted a comprehensive evaluation of state-of-the-art frontier models to reveal the pervasive trade-offs between success and compliance.

Yiyang Zhao, Zhuo Zhang, Qingxuan Le +2

Fudan University Shanghai, China · Shanghai Academy of AI for Science Shanghai, China · Shanghai Artificial Intelligence Laboratory Shanghai, China +1

Multi-Agent LLM Systems AI Agent Safety AI Agent Safety Benchmarks

Jun 4, 2026cs.AI

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents

Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal model state and environment context. We study reward-hacking monitors in ReAct-style agents acting in Gameable ALFWorld and WebShop. Agents are instrumented with activation-based reward-hack scores, token-level entropy, and decision-context features. We find that adapters fine-tuned on \textit{School-of-Reward-Hacks} dataset can transfer reward-hack tendencies into agentic action selection, especially when the environment exposes proxy-reward affordances. However, mitigating such behavior cannot rely on activation dynamics alone. High reward-hack activation identifies a latent policy state, but does not necessarily imply an immediate exploit action. Across next-step prediction tasks, entropy and context-calibrated internal features improve risk estimation over reward-hack activation alone. Activation-direction steering further reduces proxy-exploit behavior in selected mixed-adapter regimes. Overall, our results support context-calibrated internal monitoring for agents: reward-hack activation identifies a latent policy state, while entropy and decision context help determine when that state becomes risky action.

Patrick Wilhelm, Odej Kao

Distributed Operating Systems, Technische Universität Berlin, Berlin, Germany · BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany

Reward Hacking AI Agent Safety Mechanistic Interpretability AI Agent Monitoring

Jun 3, 2026cs.LG

PreAct-Bench: Benchmarking Predictive Monitoring in LLMs

Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective. While existing safety research has focused on detecting unethical behavior from complete trajectories, this paradigm is fundamentally retrospective: it identifies harm only after it has already occurred. In this work, we study a critical yet overlooked safety task, which we term Predictive Monitoring: given only a partial action trajectory, can a model infer whether it will culminate in an unethical action before the overt action is executed? To support this task, we present PreActBench, a benchmark of 1,000 paired ethical and unethical action trajectories spanning five domains. We evaluate a range of LLMs, safety guardrail models, and latent probing methods across varying fractions of the action trajectory using our Prefix Foresight F1 metric. Results show that while humans achieve promising performance, predictive monitoring remains challenging even for strong models, highlighting the need for future-oriented risk reasoning in LLM safety.

Hainiu Xu, Italo Luis da Silva, Jiangnan Ye +7

King’s College London · National University of Singapore · Southern University of Science and Technology +3

LLM Safety Benchmarks Moral Reasoning in Language Models AI Agent Safety AI Agent Benchmarks LLM Safety Evaluation AI Agent Safety Benchmarks

Jun 3, 2026cs.AI

Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety

An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately. AI control is a safety framework for deploying capable but untrusted AI agents under the oversight of a weaker, trusted monitor and a limited human audit budget. Control evaluations stress-test these protocols by pitting a red-team attack policy against the blue-team monitor, but current evaluations typically assume attackers that do not strategically select when to attack. We study this capability, attack selection, in agentic settings by decomposing attack decisions into a start policy, which decides when an attacker should attack, and a stop policy, which decides when an attacker should abort an ongoing attack. Across two agentic settings, BashArena and LinuxArena, both policies substantially lower measured empirical safety without changing the underlying attack capability. At a 1% audit budget, our start policy reduces safety by 20pp on both BashArena and LinuxArena, and our stop policy reduces safety by 20pp on BashArena and 28pp on LinuxArena. These reductions should be interpreted as upper bounds on the effect of attack selection. Existing control evaluations may therefore yield overly optimistic safety estimates against selective attackers. We recommend that future evaluations, system cards, and safety cases elicit attack selection to produce more realistic safety estimates.

Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad +3

University of Oxford · Mentorship for Alignment Research Students (MARS), CAISH · Georgia Institute of Technology +3

Adversarial Attacks AI Agent Safety AI Agent Security Benchmarks AI Control AI Safety Evaluation AI Agent Safety Benchmarks

Jun 3, 2026cs.CR

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel. We ask whether those techniques, reproduced as hand-crafted templates, still work against current frontier CUAs. We release CUA-HandCrafted, a public benchmark of 793 episodes spanning 24 multi-step web tasks, 56 attack templates, 8 attack families, and 4 system-prompt configurations. Against Claude Sonnet 4.6 and GPT-5.4 we measure 0/140 multi-step attack success (Clopper-Pearson 95% upper bound 2.60%); a prompt ablation shows this resistance lives in the model weights. Yet it does not generalize: on a sister coding-agent benchmark (SkillBench), the same weights fall to hand-crafted skill-injection at up to 100%. We argue that the literature's high ASR is largely attributable to RL-optimized injection text rather than the attack categories, and that frontier safety hardening is domain-conditioned, specific to the heavily-targeted browser surface. Reporting techniques without releasing the optimized strings, or extrapolating browser-domain safety to other CUA modalities, makes published ASR numbers unreproducible.

Nicholas Saban

Patronus AI · University of California, Berkeley

Computer-Use Agents AI Agent Safety AI Agent Security Benchmarks Prompt Injection Attacks Prompt Robustness

Jun 3, 2026cs.AI

The Digital Apprentice: A Framework for Human-Directed Agentic AI Development

Agentic AI deployments face a recurring design tension: heavy human oversight limits scale, while broad autonomy outruns accountability. Neither posture provides the governance infrastructure required for responsible delegation. We present the Digital Apprentice, a framework for scalable, safe AI agency in which autonomy is earned, not assumed. The Digital Apprentice is a developmental learner that internalizes the tacit methodology of a directing human, graduating through per-skill autonomy tiers only when empirical evidence justifies it. The result is an agent that becomes genuinely useful over time while remaining aligned to a specific human's standards. Three architectural components make this possible. (1) Methodology capture, distilling a directing professional's tacit approach into structured assets. (2) Authorization, with autonomy escalation gated by explicit human approval. (3) Continuous alignment, correcting drift at runtime and converting each correction into owned preference data. We instantiate this framework as an inference-time control plane. We mathematically model the quality framework and discuss policies and techniques designed to raise quality. We apply the framework to an open professional corpus, and we show how catching data drift and applying a different technique at runtime recovers degraded quality dimensions under traffic shift. The implication extends beyond any single application. We believe these three pillars, stitched together as a system, form a safer and more viable path to agentic systems that can scale without sacrificing trust.

Travis Weber, Rohit Taneja

Pheo Inc

AI Agent Safety Human-in-the-Loop AI Shared Autonomy Agent Skill Learning AI Agent Governance

Jun 2, 2026cs.RO

PerceptTwin: Semantic Scene Reconstruction for Iterative LLM Planning and Verification

Simulation environments are useful for both robot policy learning and planning verification and validation. Traditionally, the process of creating a simulation was onerous. Creating a bespoke simulation environment for each individual environment that a robot would operate in was simply infeasible. In this work, we introduce PerceptTwin, a fully automatic pipeline that constructs interactive simulations directly from semantic scene representations produced by a robot's perception stack. PerceptTwin combines open-vocabulary object maps with 3D asset generation, affordance prediction, and commonsense condition checking. These interactive simulations can be used to validate and refine plans before they are executed on the robot hardware. Borrowing from the AI alignment literature, we also introduce an LLM judge that verifies plan correctness and alignment with human preferences. Experiments show that PerceptTwin feedback allows LLM planners to refine plans, enhance safety, and resist harmful black-box prompting attacks. In our suite of tasks, PerceptTwin improves plan success by an average of approximately 39% for GPT5, GPT5Mini, and GPT5Nano planners. Additionally, PerceptTwin also improves human plan verification by up to 18% on average for plans that fail due to unfilled skill preconditions. Our results demonstrate the potential of open-vocabulary scene simulation from robot perception as a foundation for safer, more reliable robot planning.

Charlie Gauthier, Sacha Morin, Liam Paull

Department of Computer Science and Operations Research, Universit´e de Montr´eal, Montr´eal, QC, Canada. · Mila - Quebec AI Institute, Montr´eal, QC, Canada. · CIFAR AI Chair.

Large Language Model-Based Robot Planning Robotics Simulation AI Agent Safety Robot Task Planning

Jun 2, 2026cs.CY

Agentic Safety is an Epistemic Property, Not a Behavioral One

Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming. These methods are necessary, but they primarily certify snapshots of system behavior. As AI systems become more capable, dynamic, embodied, and self-improving, this snapshot view becomes incomplete: safety depends not only on whether a system behaves acceptably now, but whether it remains correctable as it learns, adapts, acts, and modifies itself over time. This paper argues that safety should therefore be treated as an epistemic property of the evolving learner, not merely a behavioral property of the current policy. We introduce teachability as the capacity to preserve future corrective leverage under bounded human, institutional, or environmental intervention. We argue that advanced systems can retain visible competence while eroding the representational, algorithmic, or meta-decision conditions needed for future correction. Safe advanced AI systems must not only behave acceptably now; they must remain teachable later.

Charles L. Wang, Keir Dorchen, Peter Jin

1Columbia University, New York, NY, USA · 2Pelagic Platforms

AI Alignment AI Agent Safety Self-Improving Agents

Jun 2, 2026cs.CV

VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring

As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible consequences that digital errors do not. We introduce the Vision-Language Embodied Safety Agent (VLESA), a framework that monitors human activities from egocentric video and triggers real-time safety interventions when dangerous actions are predicted. VLESA addresses intent-dependent safety where identical actions can be safe or dangerous depending on context. A dataset pairing egocentric frames with goal-conditioned safety annotations is introduced, enabling a goal-conditioned safety Q-filter trained via GRPO that evaluates actions with respect to inferred intent without retraining. On top of that, an intent-action prediction agent is proposed to jointly infer goals and predict future actions from video. On the ASIMOV-2.0 benchmark, VLESA achieves higher intervention accuracy at the exact ground-truth frame compared to baselines, while the GRPO-trained Q-filter improves action safety by over 41 percentage points through goal-conditioned constrained decoding. Code is available at https://github.com/HanjiangHu/VLESA.

Hanjiang Hu, Yiyuan Pan, Jiaxing Li +5

Carnegie Mellon University · Harvard University · Mitsubishi Electric Research Laboratories

Egocentric Video Understanding AI Agent Safety

Jun 2, 2026cs.AI

LAP: An Agent-to-Instrument Protocol for Autonomous Science

Autonomous science is moving from demonstration to infrastructure. Large language model agents now plan experiments, and self-driving laboratories execute them. Yet every such system rebuilds the link between the reasoning agent and the physical instrument from scratch, against fragmented vendor SDKs and standards built for deterministic software clients rather than probabilistic, goal-directed agents. Recent agent-interoperability protocols clarify two of the three edges of an agentic ecosystem (Anthropic's Model Context Protocol (MCP) standardizes the agent-to-tool edge, and Google's Agent2Agent (A2A) the agent-to-agent edge), but neither models the agent-to-instrument edge, where operations are stateful, safety-critical, exclusively owned, physically embodied, and produce measurements with units, calibration, and uncertainty. We present the Lab Agent Protocol (LAP), a protocol design that fills this gap. LAP retains A2A's peer-to-peer, discovery-first, task-lifecycle structure and adds four physical-world primitives: (i) the InstrumentCard, a signed capability and physical-limit description; (ii) first-class reservation for exclusive instrument and sample locking; (iii) a safety-fence handshake with operator-confirmation tokens cryptographically bound to a specific task and its parameters, gating hazardous and irreversible operations; and (iv) a MeasurementResult schema that makes every result physically typed (QUDT/UCUM), calibration-anchored, uncertainty-bearing, and reproducible by construction. We specify roles, a six-layer architecture, the JSON-RPC method set, the task and safety state machines, the error model, and cross-laboratory federation, and walk a closed-loop autonomous campaign through the protocol end-to-end. LAP is transport-compatible with the A2A/MCP ecosystem and encapsulates rather than replaces existing device standards such as SiLA 2 and OPC-UA.

Linwu Zhu, Liqiang Gao, Yan Chen +2

Shiyanjia Lab

AI Agents for Scientific Discovery Agent Communication Protocols AI Agent Safety Laboratory Automation Autonomous Experimentation

Jun 2, 2026cs.LG

RUBAS: Rubric-Based Reinforcement Learning for Agent Safety

The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation. Existing alignment methods often rely on coarse refusal signals or static supervision, making it difficult to balance safety with useful tool execution across diverse agentic risks. We introduce RUBAS, a rubric-based reinforcement learning framework for agent safety. RUBAS decomposes agent behavior into four dimensions: tool-use safety, argument safety, response safety, and helpfulness. These structured rubrics provide fine-grained and interpretable rewards over complete agent trajectories, enabling reinforcement learning to optimize safe tool use while preserving task completion. Extensive experiments across multiple agent safety benchmarks and models show that RUBAS improves safety over standard alignment baselines, reduces tool-grounded hallucinations, and maintains competitive utility. Our results suggest that multi-dimensional rubric rewards provide an effective training signal for aligning LLM agents in safety-critical tool-use settings.

Xian Qi Loye, Qinglin Su, Zhexin Zhang +5

The Conversational AI (CoAI) group, DCST, Tsinghua University · Huawei Noah’s Ark Lab

Reinforcement Learning AI Agent Safety Rubric-Based RL LLM Agent Training LLM Agent Safety RL for Tool Use

Jun 2, 2026cs.AI

Solipsistic Superintelligence is Unlikely to be Cooperative

AI's central challenge is shifting from capability to coexistence. The dominant paradigm in AI research focuses on developing powerful agents that treat the world as an exogenous and stationary source of feedback. We contend that superintelligence, an extremely capable task solver, born out of such a solipsistic approach to AI design, is unlikely to be cooperative. Deploying AI systems induces endogenous non-stationarity, resulting in a train-test-deploy gap where historical distributions diverge from the deployment context. We refer to this as the self-undermining property of unilateral optimization. Closing this gap requires AI that participates in cooperation: the equilibrium-selection process through which multiple actors navigate their interdependence. We call for a non-solipsistic research paradigm that treats this interdependence as a core design principle rather than approaching cooperation as a task to solve. This entails building dynamic evaluation testbeds involving adaptive counterparties, treating institutions as design primitives, and preserving human agency as a structural feature of the systems we build.

Rakshit S Trivedi, Natasha Jaques, Logan Cross +2

Independent Researcher, CA, USA · University of Washington, Seattle, WA, USA · Google Deepmind, London, UK.

AI Alignment Multi-Agent Collaboration AI Agent Safety Human-Centered AI

Jun 2, 2026cs.ET

Glass Box at Orbit: A Constitutional AI Verification Framework for Trustworthy Autonomous CubeSat Intelligence

The space industry is quietly building toward something nobody has fully reckoned with: orbital data centers running thousands of autonomous AI workloads with no human in the loop, 550 km above the Earth. Microsoft, AWS, and a growing list of orbital computing ventures are moving cloud-scale processing off the ground and into orbit. What none of them have answered yet is the governance question -- when autonomous AI systems at orbital data center scale make wrong decisions in space, what stops those decisions before they become irreversible? We introduce Glass Box: a runtime constitutional AI verification layer that intercepts every candidate action from an onboard AI policy and evaluates it against six physics-grounded constitutional constraints and seven Linear Temporal Logic (LTL) safety invariants before a single command reaches any spacecraft subsystem. Every approved action carries a weighted explainability score E(a_t) in [0,1] and a complete constitutional audit log. We demonstrate Glass Box within Project October: a fully simulated five-layer autonomous orbital intelligence architecture for CubeSat-class spacecraft. We prove that Glass Box verification overhead is O(N_c) in the number of constitutional rules, independent of model size or spacecraft state dimension. We present a complete formal specification of the constitutional constraint grammar, seven LTL safety invariants verified by Z3 and NuSMV model checking, and a detailed worked example of Glass Box intercepting an unsafe inference request at eclipse-entry under degraded battery state. As orbital computing scales toward data center infrastructure, runtime constitutional verification is no longer a research novelty -- it is mission-critical safety infrastructure that every autonomous orbital platform will eventually require.

Karthik Barma, Anil Sanneboyina, V C Premchand Yadav

Khoury College of Computer Sciences · Northeastern University · Boston, MA 02115, USA +3

AI Alignment AI Agent Safety Formal Verification AI Agent Governance Runtime Verification