AI models and papers trending on October 1, 2026
The edition of this day as it was recorded: the most upvoted papers of the daily list.
On Thursday, October 1, 2026 the most upvoted paper was "The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation", with 372 votes. 11 of the 15 leading papers had a code repository attached. No model list exists for this day: Hugging Face does not publish past trending lists, and our collector had not started yet.
Papers only · rebuilt on 2026-10-03 09:16 UTC from the Hugging Face daily papers archive
Papers
- 372
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
arXiv 2609.36484 (opens in a new tab)Code (opens in a new tab)
- 335
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Rutgers UniversityarXiv 2609.39102 (opens in a new tab)
- 273
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Stanford NLParXiv 2609.38721 (opens in a new tab)
- 209
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
AmazonarXiv 2609.34563 (opens in a new tab)Code (opens in a new tab)
- 127
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Beijing Academy of Artificial IntelligencearXiv 2609.38288 (opens in a new tab)Code (opens in a new tab)
- 110
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
- 104
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Minnesota NLParXiv 2609.40340 (opens in a new tab)Code (opens in a new tab)
- 95
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
University of California, Santa BarbaraarXiv 2609.40325 (opens in a new tab)Code (opens in a new tab)
- 80
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
ApodexarXiv 2609.38143 (opens in a new tab)Code (opens in a new tab)
- 78
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
RSIGamearXiv 2609.39045 (opens in a new tab)Code (opens in a new tab)
- 70
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Shanghai Jiao Tong UniversityarXiv 2609.38334 (opens in a new tab)Code (opens in a new tab)
- 61
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Southern University of Science and TechnologyarXiv 2609.39578 (opens in a new tab)
- 59
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
KAIST AIarXiv 2609.38177 (opens in a new tab)Code (opens in a new tab)
- 53
More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models
Jilin UniversityarXiv 2609.38827 (opens in a new tab)Code (opens in a new tab)
- 51
LoopVL: Recurrent Visual Intelligence
Renmin University of ChinaarXiv 2609.38426 (opens in a new tab)Code (opens in a new tab)
Models
No model list exists for this day. Hugging Face does not publish past trending lists, so days before the collector started carry papers only.
About the archive
How far back does the archive go?
Model lists exist from the first day the collector ran: Hugging Face does not publish past trending lists, so they cannot be rebuilt. Paper lists for earlier days were rebuilt from the Hugging Face daily papers archive, and those days are marked "papers only".
What is kept for each day?
The leading models with their task, likes and downloads on that day, the models held back, and the leading papers with their upvotes. Abstracts are not duplicated in the archive; each paper links to arXiv.
Do archived numbers change?
No. A day’s record is the last collection of that day and is not rewritten afterwards. Likes and downloads you see on an archived day are the values on that day, not today’s.
How are weeks defined?
ISO 8601 weeks: Monday to Sunday, numbered so that week 1 contains the first Thursday of the year. The address /week/2026-40 is week 40 of 2026.