Daily papers of 26 Oct 2026

Daily Papers

Here is the selection of papers for today (26 Oct):

• Reading, Writing, Sharing, and Interacting with the World through Video (216 ▲)
• UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents (47 ▲)
• HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games (38 ▲)
• RSIHub: A Composable Framework for Agent-Evolution Methods (34 ▲)
• RynnUnify: Towards Unified Embodied Brain (33 ▲)
• Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs (21 ▲)
• Every Weight Is a Path of Shared Discrete Decisions (19 ▲)
• Dual Exam: Controlled Evaluation of Multimodal Agents and World Models (16 ▲)
• DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model (16 ▲)
• On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models (12 ▲)
• DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation (12 ▲)
• TenetBench: A Clause-Anchored Russian Corpus for Evaluating Language Models against Professional Codes of Ethics (12 ▲)
• And 30 more papers

NEW - I'm opening Daily Papers! If you're a researcher you can now submit your peers' papers to be featured in Daily Papers directly. Use this page to do so: huggingface.co/papers/submit.

Until next time,
AK and the research community