arXiv AI June 2, 2026 By Yuta Kobayashi, Zilin Jing, Jiayu Yao, Hongseok Namkoong, Shalmali Joshi

Learning-To-Measure: In-Context Active Feature Acquisition

arXiv:2510. 12624v2 Announce Type: replace-cross Abstract: Active feature acquisition (AFA) is a sequential decision-making problem where the goal is to improve model performance for test instances by adaptively selecting which features to acquire.

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 Computer Vision

Sep 1

Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning

arXiv:2608.30316v1 Announce Type: new Abstract: Existing class-incremental learning methods struggle in multi-label scenarios (MLCIL) due to the inherent contradiction of learning objectives arising...

By Aoting Zhang, Dongbao Yang, Chang Liu, Xiaopeng Hong, Can Ma, Yu Zhou

rag benchmarks

arXiv Machine Learning

4d ago

Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients

The paper introduces Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients (NM-PPG), a method that relaxes the feature acquisition process to allow continuous, low‑variance policy gradients over the entire acquisition trajectory. It incorporates a straight‑through rollout that mimics discrete acquisitions during inference while enabling end‑to‑end training, and provides an average‑case upper bound on gradient variance to guide temperature sharpening. Experiments on synthetic and real datasets show that NM-PPG outperforms existing active feature acquisition baselines.

By Linus Aronsson, Morteza Haghir Chehreghani

benchmarks

arXiv Computer Vision

Aug 21

CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning

arXiv:2507. 09471v4 Announce Type: replace Abstract: Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.

By Lingfeng He, De Cheng, Zhiheng Ma, Huaijie Wang, Dingwen Zhang, Nannan Wang, Xinbo Gao

fine-tuning safety

arXiv AI

Aug 11

Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training

arXiv:2608. 09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization.

By Ting Zhou, Zhenqing Ling, Daoyuan Chen, Qianli Shen, Yilun Huang, Ying Shen, Yaliang Li

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jul 14

Neural Active Learning Meets the Partial Monitoring Framework

arXiv:2405. 08921v2 Announce Type: replace Abstract: We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors.

By Maxime Heuillet, Ola Ahmad, Audrey Durand

agents benchmarks

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