arXiv Machine Learning

Active Curriculum Refinement for Reinforcement Learning

The paper introduces PATH, a curriculum‑learning framework that actively refines reinforcement learning by exploiting the directed acyclic curriculum graph formed by prerequisite relations among environments. PATH first expands coverage by sampling diverse curriculum paths and then reallocates training toward regions that remain unmastered. Experiments across diverse environments demonstrate that explicitly leveraging the graph structure leads to strong robustness and generalization.

arXiv Machine Learning

Sep 14

CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models

CanvasAnneal is a curriculum‑guided reinforcement learning framework designed to improve Diffusion Language Models (DLMs) on complex reasoning and tool‑use tasks. It starts training by injecting reasoning traces from a stronger teacher model into the diffusion canvas, then gradually reduces this guidance so the model learns to generate reasoning independently. Experiments on mathematical reasoning and tool‑use benchmarks show that CanvasAnneal outperforms standard diffusion RL methods such as diffu‑GRPO on tasks like MATH500, Countdown, and Tau2, and accelerates reward improvement, though the gains vary by task.

By Blake Olson, Yuhang Song, Emmett McQuinn, Yuan Shangguan

llms diffusion reinforcement-learning benchmarks

arXiv AI

Oct 5

EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation

EVOL is a framework that uses a knowledge‑tracing simulator to generate per‑learner expert demonstrations via evolutionary search, and then trains a deployment‑free policy that distills these demonstrations into a feed‑forward learner. The method employs an asymmetric actor‑critic architecture, where the actor plans blindly as in real deployment while the critic has access to privileged simulator state during training. Across three educational datasets and varying path lengths, EVOL outperforms eight baselines and shows that the quality of evolutionary experts, rather than the imitation objective, drives final performance.

By Geonwoo Bang, Dongho Kim, Moohong Min

llms reinforcement-learning robotics

arXiv Machine Learning

Aug 14

Trajectory First: A Curriculum for Discovering Diverse Policies

arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.

By Cornelius V. Braun, Sayantan Auddy, Marc Toussaint

agents reinforcement-learning robotics safety

arXiv AI

3d ago

GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning

arXiv:2602.02518v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many knowledge sources on the Web, such as sc...

By Yuyang Bai, Zhuofeng Li, Ping Nie, Jianwen Xie, Yu Wang, Yu Zhang

llms agents 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

Jul 24

PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

arXiv:2607. 21419v1 Announce Type: new Abstract: In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimization.

By Yipeng Shi, Zhipeng Ma, Yue Wang, Qitai Tan, Yang Li, Peng Chen, Zhengzhou Zhu

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 2

Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers

The paper introduces SAGE, a framework that selectively queries a Vision‑Language Model (VLM) teacher only when the learner is uncertain, using the teacher’s suggestions to guide training and distill them into a lightweight reinforcement learning policy. SAGE weights teacher actions by environment‑derived advantages, allowing the policy to improve beyond the imperfect VLM. Experiments on sparse‑reward visual reasoning and navigation tasks show that the learned policies can act without VLM guidance at evaluation, reduce VLM usage during training, and sometimes outperform the teacher itself.

By Matteo Merler, Giovanni Bonetta, Davide Zago, Rossella Cancelliere, Bernardo Magnini

llms agents reinforcement-learning efficiency multimodal

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

Jul 7

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

arXiv:2602. 21534v3 Announce Type: replace Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks.

By Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi, Ruoyan Li, Kaiqiao Han, Chenyi Tong, Haoran Deng, Renliang Sun, Alexander Taylor, Yanqiao Zhu, Jason Cong, Yizhou Sun, Wei Wang

llms agents reinforcement-learning

arXiv AI

Aug 18

Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain

arXiv:2608. 16164v1 Announce Type: new Abstract: Training locomotion policies for complex unstructured terrain requires a curriculum to avoid early exploration failures.

By Rocky Liu, Tengyu Liu, Baoxiong Jia, Fangwei Zhong, Xinyi Tong, Hongzhao Xie, Siyuan Huang

robotics

arXiv AI

Jun 30

Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR

arXiv:2606. 25178v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science.

By Yongjin Yang, Jiarui Liu, Yinghui He, Lechen Zhang, Bernhard Sch\"olkopf, Zhijing Jin

reinforcement-learning safety

arXiv AI

Jun 15

Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning

arXiv:2509. 18930v3 Announce Type: replace-cross Abstract: Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning.

By Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki, Bruno Lacerda, Nick Hawes

reinforcement-learning

Related stories