arXiv Machine Learning By Aarav Bedi

Phase-Localized Curation Does Not Help: A Negative Result on Per-Phase Metric Selection for Demonstration Filtering

Read the original on arXiv Machine Learning →

arXiv:2606. 15064v1 Announce Type: new Abstract: Manipulation demonstrations have temporal phase structure, and a natural hypothesis is that demonstration-curation metrics should be applied within phases rather than globally.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jul 7

Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry

arXiv:2607. 03702v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajectories: full retries incur high interaction costs, while experience retrieval tends to dilute critical experience signals.

By Weiyang Guo, Zesheng Shi, Longhui Zhang, Zeen Zhu, Min Zhang, Jing Li
arXiv Machine Learning
Aug 4

Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit

arXiv:2608. 02302v1 Announce Type: cross Abstract: Long-horizon coding-agent trajectories are poorly matched to the credit units available to train on: a single action has no stable value, an episode label merges productive exploration with abandoned directions, and a fixed window cuts where the logging mechanics fall.

By Jingxi Wei