Position: AI Safety Must Embrace an Antifragile Perspective

• URL: http://arxiv.org/abs/2509.13339v1
• Date: Thu, 11 Sep 2025 14:01:43 GMT
• Title: Position: AI Safety Must Embrace an Antifragile Perspective
• Authors: Ming Jin, Hyunin Lee,
• Abstract summary: This position paper contends that modern AI research must adopt an antifragile perspective on safety.<n>We argue that an antifragile approach is pivotal for the long-term reliability of open-ended ML systems.
• Score: 8.304578789644124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This position paper contends that modern AI research must adopt an antifragile perspective on safety -- one in which the system's capacity to guarantee long-term AI safety such as handling rare or out-of-distribution (OOD) events expands over time. Conventional static benchmarks and single-shot robustness tests overlook the reality that environments evolve and that models, if left unchallenged, can drift into maladaptation (e.g., reward hacking, over-optimization, or atrophy of broader capabilities). We argue that an antifragile approach -- Rather than striving to rapidly reduce current uncertainties, the emphasis is on leveraging those uncertainties to better prepare for potentially greater, more unpredictable uncertainties in the future -- is pivotal for the long-term reliability of open-ended ML systems. In this position paper, we first identify key limitations of static testing, including scenario diversity, reward hacking, and over-alignment. We then explore the potential of antifragile solutions to manage rare events. Crucially, we advocate for a fundamental recalibration of the methods used to measure, benchmark, and continually improve AI safety over the long term, complementing existing robustness approaches by providing ethical and practical guidelines towards fostering an antifragile AI safety community.

Related papers

• The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies [57.387081435669835]
  Multi-agent systems built from large language models offer a promising paradigm for scalable collective intelligence and self-evolution.<n>We show that an agent society satisfying continuous self-evolution, complete isolation, and safety invariance is impossible.<n>We propose several solution directions to alleviate the identified safety concern.
  arXiv  Detail & Related papers  (2026-02-10T15:18:19Z)
• Conformal Reachability for Safe Control in Unknown Environments [29.315278038378835]
  We develop a probabilistic verification framework for unknown dynamical systems.<n>We use conformal prediction to obtain valid uncertainty intervals for the unknown dynamics at each time step.<n>We also develop an algorithmic approach for training control policies that optimize nominal reward while also maximizing the planning horizon.
  arXiv  Detail & Related papers  (2026-02-03T18:01:38Z)
• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search [72.87861928940929]
  Boundary-Aware Policy Optimization (BAPO) is a novel RL framework designed to cultivate reliable boundary awareness without compromising accuracy.<n>BAPO introduces two key components: (i) a group-based boundary-aware reward that encourages an IDK response only when the reasoning reaches its limit, and (ii) an adaptive reward modulator that strategically suspends this reward during early exploration, preventing the model from exploiting IDK as a shortcut.
  arXiv  Detail & Related papers  (2026-01-16T07:06:58Z)
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
  Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
  arXiv  Detail & Related papers  (2025-12-24T15:01:26Z)
• CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention [68.95008546581339]
  Existing decoding-time interventions, such as Contrastive Decoding, often force a severe trade-off between safety and response quality.<n>We propose CARE, a novel framework for decoding-time safety alignment that integrates three key components.<n>The framework achieves a superior balance of safety, quality, and efficiency, attaining a low harmful response rate and minimal disruption to the user experience.
  arXiv  Detail & Related papers  (2025-09-01T04:50:02Z)
• Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs [19.045128057653784]
  We introduce time-to-unsafe-sampling, a novel safety measure for generative models.<n> unsafe outputs are often rare in well-aligned models and thus may not be observed under any feasible sampling budget.<n>We propose a novel calibration technique to construct a lower predictive bound (LPB) on the time-to-unsafe-sampling of a given prompt with rigorous coverage guarantees.
  arXiv  Detail & Related papers  (2025-06-16T15:21:25Z)
• Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy Regularization [47.30677525394649]
  We analyze the interplay between two well-established techniques in model-free reinforcement learning: entropy regularization and constraints penalization.<n>We show that entropy regularization in constrained RL inherently biases learning toward maximizing the number of future viable actions, thereby promoting constraints satisfaction robust to action noise.<n>We conclude that the connection between entropy regularization and robustness is a promising avenue for further empirical and theoretical investigation.
  arXiv  Detail & Related papers  (2025-06-12T16:34:19Z)
• Towards provable probabilistic safety for scalable embodied AI systems [79.31011047593492]
  Embodied AI systems are increasingly prevalent across various applications.<n> Ensuring their safety in complex operating environments remains a major challenge.<n>This Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications.
  arXiv  Detail & Related papers  (2025-06-05T15:46:25Z)
• Feasibility-Aware Pessimistic Estimation: Toward Long-Horizon Safety in Offline RL [14.767273209148545]
  We propose a novel framework Feasibility-Aware offline Safe Reinforcement Learning with CVAE-based Pessimism (FASP)<n>We employ Hamilton-Jacobi (H-J) reachability analysis to generate reliable safety labels.<n>We also utilize pessimistic estimation methods to estimate the Q-value of reward and cost.
  arXiv  Detail & Related papers  (2025-05-13T02:32:49Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Towards Safe Policy Improvement for Non-Stationary MDPs [48.9966576179679]
  Many real-world problems of interest exhibit non-stationarity, and when stakes are high, the cost associated with a false stationarity assumption may be unacceptable. We take the first steps towards ensuring safety, with high confidence, for smoothly-varying non-stationary decision problems. Our proposed method extends a type of safe algorithm, called a Seldonian algorithm, through a synthesis of model-free reinforcement learning with time-series analysis.
  arXiv  Detail & Related papers  (2020-10-23T20:13:51Z)
• Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Framework [30.58186749790728]
  We propose a theoretically-justified approach to maintaining safety in the presence of dynamics uncertainty. Our framework guarantees the high-probability satisfaction of all constraints at all times jointly. This theoretical analysis also motivates two regularizers of last-layer meta-learning models that improve online adaptation capabilities.
  arXiv  Detail & Related papers  (2020-08-26T17:39:58Z)

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.