Hugging Face Trending Papers August 31, 2026

Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry

Read the original on Hugging Face Trending Papers →

The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.

reinforcement-learning

arXiv Machine Learning

Sep 1

Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry

arXiv:2608.30442v1 Announce Type: new Abstract: Recent offline reinforcement learning (RL) studies report policies that outperform physician decisions on clinical outcomes. We conduct a systematic, p...

By Kihun Rhee

reinforcement-learning

arXiv AI

Aug 5

Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents

arXiv:2608. 03606v1 Announce Type: new Abstract: Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence.

By William Bolton, Philip Torr

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 5

A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR

arXiv:2606. 05932v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier.

By Yuze Gao

reinforcement-learning safety

arXiv AI

6d ago

From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training

arXiv:2609. 31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy.

By Wang Jingxin

llms fine-tuning multimodal

arXiv AI

Aug 7

From Continuous Predictors to Clinical Thresholds: Early Evidence on Performance Trade-offs of Guideline-Based Categorisation for Ischaemic Stroke Outcome Prediction

arXiv:2608. 05203v1 Announce Type: new Abstract: Machine learning models achieve strong predictive accuracy for 90-day outcome prediction in acute ischaemic stroke, yet clinical adoption is limited by the misalignment of model explanations with clinicians' reasoning.

By Esra Zihni, Katryna Cisek, Hamzah Ziadeh, Hendrik Knoche, Robert Mikulik, John D. Kelleher

arXiv Machine Learning

Jun 5

Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents

arXiv:2606. 05263v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut actions that satisfy terminal checks.

By Renwei Meng

agents reinforcement-learning

One email a morning, machine-written

Related stories

Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry

Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents

A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR

From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training

From Continuous Predictors to Clinical Thresholds: Early Evidence on Performance Trade-offs of Guideline-Based Categorisation for Ischaemic Stroke Outcome Prediction

Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents