arXiv AI October 9, 2026 By Yichun Ye, He Zhang, Ye Tian, Jian Sun

Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition

The paper introduces a Lamarckian evolutionary framework for discovering autonomous driving training strategies by replacing surrogate-based guidance with competition among candidate scenario distributions. It formulates training strategy discovery as a multi-stage bilevel optimization problem, using Darwinian crossover, mutation, and selection at the outer level and policy learning at the inner level, with Lamarckian inheritance enabling co‑evolution of distributions and policy capabilities. Experiments demonstrate that the full framework reduces performance loss by up to 25.07% and a distilled lightweight strategy still achieves a 19.13% reduction, revealing reusable stage‑wise patterns in training distribution value.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 16

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

arXiv:2606. 16236v1 Announce Type: new Abstract: Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training.

By Ekasit Usaratniwart, Xilin Gao, Marc Ong, Youhei Akimoto

agents reinforcement-learning safety

arXiv AI

Oct 2

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

ActiveSaddler introduces automated curriculum learning for harness optimization, treating the evolving training curriculum as a non‑stationary bandit problem. It identifies reusable failure patterns, estimates learning progress for each, and balances revisiting known weaknesses with exploring new scenarios, allowing the curriculum to co‑evolve with the harness. Experiments on GAIA2 and Terminal‑Bench 2.0 show consistent improvements in harness performance, with Pass@1 gains of 4.4 and 7.5 percentage points over fixed‑order baselines.

By Sungho Park, Wonjoong Kim, Jue Zhang, Wook-Shin Han, Pengfei Gao, Chanyoung Park, Yongqiang Yao, Rao Fu, Elsie Nallipogu, Qingwei Lin, Victor R\"uhle

llms agents reinforcement-learning

arXiv AI

Jun 15

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals

arXiv:2601. 19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks.

By Octavio Pappalardo

agents reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jul 27

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.

By Shujin Wu, Cheng Qian, Xiusi Chen, Heng Ji

llms reinforcement-learning benchmarks

arXiv AI

Aug 25

Scaling Curriculum Learning For Autonomous Driving

arXiv:2608.22549v1 Announce Type: new Abstract: Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic...

By Cevahir Koprulu, David Paz, Feng Tao, Yuliang Guo, Xinyu Huang, Ufuk Topcu, Liu Ren

agents reinforcement-learning robotics efficiency benchmarks

arXiv AI

1d ago

Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI

The paper presents a theoretical framework comparing three evolutionary paradigms—Darwinian, Lamarckian, and agent-directed evolution—in the context of AI. It shows that when learning is effective, agent-directed evolution can accelerate adaptation by generating and evaluating behavioral variants, but this speed can also lead to convergence on misspecified objectives. The authors argue that independent evaluation and oversight are essential to ensure that AI’s self-directed improvements remain aligned with intended goals.

By Andrew W. Lo, Chaoyi Zhao

agents safety

One email a morning, machine-written

Related stories

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

Scaling Curriculum Learning For Autonomous Driving

Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI