paper-with-me

홈 › Papers

Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery

2026-03-30 · Peiran Li, Fangzhou Lin, Shuo Xing, Jiashuo Sun, Dylan Zhang, Siyuan Yang, Chaoqun Ni, Zhengzhong Tu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.29045

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Falsification-Based Robust Adversarial Reinforcement Learning

2020-07-01 · Xiao Wang, Saasha Nair, Matthias Althoff

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+2

STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning

2025-08-26 · Chenghao Wu, Ruiyang Ren, Junjie Zhang, Ruirui Wang 외 arxiv

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 Inference

Learning to falsify automated driving vehicles with prior knowledge

2021-01-25 · Andrea Favrin, Vladislav Nenchev, Angelo Cenedese

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 Driving

Parallel and Multi-Objective Falsification with Scenic and VerifAI

2021-07-09 · Kesav Viswanadha, Edward Kim, Francis Indaheng, Daniel J. Fremont 외

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

2021-05-27 · IEEE/ACM 43rd International Conference on Software Engineering (ICSE) 2021 5 · David Shriver, Sebastian Elbaum, Matthew B. Dwyer

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