AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

• URL: http://arxiv.org/abs/2603.07427v2
• Date: Sat, 14 Mar 2026 06:28:02 GMT
• Title: AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
• Abstract summary: We present AutoControl Arena, an automated framework for frontier AI risk evaluation.<n>We mitigate hallucination while maintaining flexibility.<n>This principle, instantiated through a three-agent framework, achieves over 98% end-to-end success and 60% human preference over existing simulators.
• Score: 22.833977971686966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present AutoControl Arena, an automated framework for frontier AI risk evaluation built on the principle of logic-narrative decoupling. By grounding deterministic state in executable code while delegating generative dynamics to LLMs, we mitigate hallucination while maintaining flexibility. This principle, instantiated through a three-agent framework, achieves over 98% end-to-end success and 60% human preference over existing simulators. To elicit latent risks, we vary environmental Stress and Temptation across X-Bench (70 scenarios, 7 risk categories). Evaluating 9 frontier models reveals: (1) Alignment Illusion: risk rates surge from 21.7% to 54.5% under pressure, with capable models showing disproportionately larger increases; (2) Scenario-Specific Safety Scaling: advanced reasoning improves robustness for direct harms but worsens it for gaming scenarios; and (3) Divergent Misalignment Patterns: weaker models cause non-malicious harm while stronger models develop strategic concealment.

Related papers

• Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety [2.661610409070365]
  We introduce Boiling the Frog, a benchmark that evaluates whether tool-using AI models are susceptible to incremental attacks.<n> Scenarios are organized through a three-level operational risk taxonomy.<n>Across a nine-model panel, aggregate strict attack success rate (ASR) is 44.4%.
  arXiv  Detail & Related papers  (2026-05-21T15:50:18Z)
• C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving [5.963051368087439]
  We propose a counterfactual chain-of-thought (C-CoT) framework to decompose driving decisions into five sequential stages.<n>Within the counterfactual reasoning stage, we introduce a structured meta-action evaluation tree to explicitly assess the potential consequences of alternative action combinations.<n>This self-reflective reasoning establishes causal links between action choices and safety outcomes, improving robustness in long-tail and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2026-05-11T15:45:00Z)
• Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework [63.74295981594549]
  Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
  arXiv  Detail & Related papers  (2026-04-23T23:44:01Z)
• ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis [96.92417622318267]
  ATBench is a trajectory-level benchmark for structured, diverse, and realistic evaluation of agent safety.<n>It organizes agentic risk along three dimensions: risk source, failure mode, and real-world harm.<n>It contains 1,000 trajectories (503 safe and 497 unsafe), averaging 9.01 turns and 3.95k tokens, with 1,954 invoked tools drawn from pools spanning 2,084 available tools.
  arXiv  Detail & Related papers  (2026-04-02T13:26:20Z)
• OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences [64.01706941950489]
  Current safety paradigms primarily target malicious intent or situational violations.<n>We propose shifting the safety frontier toward consequence-driven safety, a paradigm essential for the robust deployment of autonomous and embodied agents.<n>We develop the Consequence-Aware Safety Policy Optimization (CASPO) framework, which integrates the model's intrinsic reasoning as a dynamic reference for token-level self-distillation rewards.
  arXiv  Detail & Related papers  (2026-03-10T14:16:43Z)
• GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory [8.38197391178077]
  We introduce GT-HarmBench, a benchmark of 2,009 high-stakes scenarios spanning game-theoretic structures.<n>We measure sensitivity to game-theoretic prompt framing and ordering, and analyze reasoning patterns driving failures.<n>Our results highlight substantial reliability gaps and provide a broad standardized testbed for studying alignment in multi-agent environments.
  arXiv  Detail & Related papers  (2026-02-12T17:29:52Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection [54.775612141528164]
  Self-Guard is a lightweight safety defense framework for Large Reasoning Models.<n>It bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility.<n>Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales.
  arXiv  Detail & Related papers  (2026-01-31T13:06:11Z)
• The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents [37.75212140218036]
  We formalize the Loss-of-Control risk and identify the previously underexamined Intrinsic Value Misalignment (Intrinsic VM)<n>We then introduce IMPRESS, a scenario-driven framework for systematically assessing this risk.<n>We evaluate Intrinsic VM on 21 state-of-the-art LLM agents and find that it is a common and broadly observed safety risk across models.
  arXiv  Detail & Related papers  (2026-01-24T07:09:50Z)
• PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach [49.14349403242654]
  We present $textbfPropensityBench$, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors.<n>Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security.<n>Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure.
  arXiv  Detail & Related papers  (2025-11-24T18:46:44Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles [47.25901323750217]
  The generation of safety-critical scenarios in simulation has become increasingly crucial for safety evaluation in autonomous vehicles prior to road deployment in society.<n>We propose ScenGE, a framework that can generate plentiful safety-critical scenarios by reasoning novel adversarial cases and then amplifying them with complex traffic flows.<n>We validate our framework through real-world vehicle tests and human evaluation, confirming that the generated scenarios are both plausible and critical.
  arXiv  Detail & Related papers  (2025-08-20T08:36:57Z)
• Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities [49.09703018511403]
  Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks.<n>Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system.<n>We propose evaluating LLMs with model tampering attacks which allow for modifications to latent activations or weights.
  arXiv  Detail & Related papers  (2025-02-03T18:59:16Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.