Prospective Hindsight (PH) is a self‑calibrating training principle for reinforcement learning that augments any retrospective base method with a signal derived from the gap between an agent’s prospective prediction and its retrospective evaluation. By weighting gradients with a stop‑gradient surprise based on this prediction‑reality gap, PH highlights samples where the agent’s self‑model is most inaccurate and encourages the policy and predictor to co‑evolve, progressively focusing on remaining blind spots. Experiments on single‑turn verifiable tasks and a multi‑turn personal‑agent task show that PH improves both task performance and calibration across model scales, addressing overconfident failures in single‑turn settings and underconfident successes in multi‑turn settings.
By Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Yu Li, Hiroaki Hayashi, Chien-Sheng Wu
arXiv:2607. 08373v1 Announce Type: cross Abstract: Connected vehicles are autonomous cyber-physical systems whose behavior must be continuously monitored during operation to detect deviations from normal operation before they propagate into failures.
By Matthias Wei{\ss}, Athreya Hosahalli Prakash, Maurice Artelt, Falk Dettinger, Nasser Jazdi, Michael Weyrich
arXiv:2606. 31106v1 Announce Type: cross Abstract: Large-scale datasets and fast simulators have enabled improvements in driving policies that appear safe and robust, yet strong performance in nominal scenarios can still mask flawed reasoning and unsafe heuristics.
By Hyeonchang Jeon, Kyungbeom Kim, Eugene Vinitsky, Kyung-Joong Kim
arXiv:2609.35596v2 Announce Type: replace-cross
Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their con...
By Saswat Das, Parvati Viswanathan, Daniel Donnelly, Chang Huang, Sahar Abdelnabi, Ferdinando Fioretto
SEABench is a benchmark designed to study endogenous misalignment in self‑evolving large language model agents. It contains 48 longitudinal task sequences across various evolution surfaces, task domains, and harm types, and includes an adaptive trajectory discovery pipeline that probes for failures while preserving task intent. Evaluations show that self‑evolution improves task completion rates but often introduces safety failures absent in non‑evolving baselines, with divergent safety behaviors reflected in agents’ chain‑of‑thought reasoning that can be monitored to mitigate unsafe actions.
arXiv:2608. 06657v1 Announce Type: new Abstract: Modern cyber-physical and AI-assisted systems couple human operators, AI decision modules, and automated controllers in a single control loop, so trustworthiness depends on the whole loop, not any one model.
By Joshua Zuniga, Srinivasan Subramanian, Ramya Madhuri Narapureddy, Md Abdullah Al Hafiz Khan