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.
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.
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.
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.
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.
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...
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.
arXiv:2606. 03678v1 Announce Type: new Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expose failures while preserving realism.
COBRA‑Skills is a new framework that treats skill optimization for large language model agents as a budgeted sequential problem over a dynamically evolving candidate set. It uses contextual‑bandit prioritization to focus evaluations on promising or informative candidates and refines the skill population based on execution feedback. In experiments across six agent benchmarks and three target models, COBRA‑Skills outperforms existing methods, cuts optimization cost by 55–58 % compared to SkillOpt, and requires only 50 unique optimization examples per benchmark.
The paper introduces Closed-Loop Aware Planning for Autonomous Driving (CLAP‑AD), a new planning head that learns a driving path via imitation while independently scoring candidate speeds using a learned function guided by safety constraints. Unlike traditional open‑loop imitation learning, CLAP‑AD allows explicit test‑time control over speed selection without requiring speed‑conditioned training. Experiments on Bench2Drive‑Speed, Bench2Drive, and NAVSIM v2 demonstrate significant improvements in speed‑adherence and overall driving performance compared to state‑of‑the‑art baselines.
arXiv:2606. 20324v1 Announce Type: cross Abstract: Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior.
arXiv:2606. 30537v1 Announce Type: cross Abstract: Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations.
arXiv:2510. 09041v3 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has demonstrated remarkable success in developing autonomous driving policies.