Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery
Autonomous scientific discovery is entering a more dangerous regime: once the evaluator is frozen, a sufficiently strong search process can learn to win the exam without learning the mechanism the task was meant to reveal. This is the idea behind our title. To let the abyss stare back is to make evaluation actively push against the candidate through adaptive falsification, rather than passively certify it through static validation. We introduce DASES, a falsification-driven framework in which an Innovator, an Abyss Falsifier, and a Mechanistic Causal Extractor co-evolve executable scientific artifacts and scientifically admissible counterexample environments under a fixed scientific contract. In a controlled loss-discovery problem with a single editable locus, DASES rejects artifacts that static validation would have accepted, identifies the first candidate that survives the admissible falsification frontier, and discovers FNG-CE, a loss that transfers beyond the synthetic discovery environment and consistently outperforms CE and CE+L2 under controlled comparisons across standard benchmarks, including ImageNet.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Falsification-Based Robust Adversarial Reinforcement Learning
Reinforcement learning (RL) has achieved enormous progress in solving various sequential decision-making problems, such as control tasks in robotics. Since policies are overfitted to training environments, RL methods hav…
Autonomous VehiclesDecision Makingreinforcement-learningReinforcement Learning+2STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
While modern recommender systems are instrumental in navigating information abundance, they remain fundamentally limited by static user modeling and reactive decision-making paradigms. Current large language model (LLM)-…
Knowledge DistillationCausal InferenceLearning to falsify automated driving vehicles with prior knowledge
While automated driving technology has achieved a tremendous progress, the scalable and rigorous testing and verification of safe automated and autonomous driving vehicles remain challenging. This paper proposes a learni…
Autonomous DrivingParallel and Multi-Objective Falsification with Scenic and VerifAI
Falsification has emerged as an important tool for simulation-based verification of autonomous systems. In this paper, we present extensions to the Scenic scenario specification language and VerifAI toolkit that improve …
Reducing DNN Properties to Enable Falsification with Adversarial Attacks
Deep Neural Networks (DNN) are increasingly being deployed in safety-critical domains, from autonomous vehicles to medical devices, where the consequences of errors demand techniques that can provide stronger guarantees …
Adversarial AttackAutonomous Vehicles