Gotta Learn Fast: A new benchmark for generalization in RL

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?

arXiv:2510. 10541v2 Announce Type: replace-cross Abstract: Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).

RL²: Fast reinforcement learning via slow reinforcement learning

Certificate-Guided Evaluation of Reinforcement Learning Generalization

arXiv:2606. 00840v1 Announce Type: new Abstract: This work presents a logic-driven framework to evaluate the performance of reinforcement learning (RL) algorithms in their ability to generalize to unseen tasks.

Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR

arXiv:2606. 31813v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) and its variants enable parameter-efficient fine-tuning of large language models under the supervised fine-tuning (SFT) paradigm.

The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

arXiv:2606. 25450v1 Announce Type: new Abstract: Traditional evaluations measure a learning algorithm's final performance on an i.

Exposure-Based Reinforcement Learning to Rank

arXiv:2607. 18689v1 Announce Type: new Abstract: Reinforcement learning (RL) methods for learning-to-rank (LTR) can optimize (almost) any ranking goal, e.

RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

arXiv:2511. 07317v2 Announce Type: replace-cross Abstract: We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs).

Rethinking Groups in Critic-Free RLVR

arXiv:2606. 17250v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central paradigm for post-training large language models.

Exposure-Based Reinforcement Learning to Rank

Reinforcement learning (RL) methods for learning-to-rank (LTR) can optimize (almost) any ranking goal, e. g.

Limitations of SGD for Multi-Index Models Beyond Statistical Queries

arXiv:2602. 05704v2 Announce Type: replace Abstract: Understanding the limitations of gradient methods, and stochastic gradient descent (SGD) in particular, is a central challenge in learning theory.

How Far Can Sharpness and Complexity Jointly Explain Generalization?

arXiv:2606. 29043v1 Announce Type: new Abstract: Sharpness and complexity are two central factors in the generalization analysis of deep neural networks.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

arXiv:2606. 04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT).