This page shows the most relevant public items for cs.AI, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Aug 8, 2025 • arXiv • Jian Lu, Percy Liang, Chelsea Finn
While scaling laws for single-model LLMs are well established, the relationship between the number of collaborating agents and overall system performance remains poorly understood. This paper inves...
Paper • Feb 20, 2026 • arXiv • Sethuraman et al., AAMAS 2026 Main Track
We propose Mixture-of-Reasoning Agents (MiRA), a zero-shot multimodal framework that decomposes reasoning across three specialized agents: Visual Analyzing, Text Comprehending, and Judge. By consol...
Paper • Feb 19, 2026 • arXiv • Google DeepMind Team
We introduce Gemini 3.1 Pro, an enhanced version of the Gemini 3 series optimized for rigorous logic and long-horizon problem solving. Built on a hybrid architecture that fuses linear attention wit...
Paper • Dec 22, 2025 • arXiv • Percy Liang, Thomas K. V., Eleanor Rigby
Aligning multi-agent systems via traditional human feedback is intractable due to the sheer volume and speed of agent-to-agent interactions. We introduce a novel alignment framework utilizing Inver...
Paper • Jul 28, 2025 • arXiv • Sarah Jenkins, Esq., Wei Chen, Marcus T. Holden
The legal discovery process involves manually cross-referencing millions of pages of depositions and emails to find logical contradictions. Standard search algorithms fail to connect multi-document...
Paper • May 22, 2025 • arXiv • Wei Lin, Chen Wei, Yujin Han
One of the most persistent failure modes in autonomous Agentic AI is the 'Infinite Loop'—where an agent becomes stuck continuously re-executing a failed API call or repeating a flawed logical deduc...
Paper • Apr 16, 2025 • arXiv • Yannick LeCun, Antoine Bordes, Elena Rossi, Marcus Thorne
The propensity of large language models to hallucinate facts severely limits their deployment in autonomous agentic workflows where verification is costly. This paper introduces 'Agentic Debate,' a...
Paper • Apr 18, 2025 • arXiv • Maciej Besta, Nils Blach, Torsten Hoefler
While Chain-of-Thought and Tree-of-Thoughts prompting greatly enhance LLM reasoning, they strictly enforce linear or hierarchical cognitive paths. We introduce Graph of Thoughts (GoT), a novel cogn...
Paper • Sep 10, 2025 • arXiv • Yao Mu, Tianyu Zheng, Percy Liang, Dan Hendrycks
As multi-agent swarms are deployed in open-ended web environments, standard static benchmarks fail to capture their vulnerability to dynamic threats and deceptive actors. We introduce AgentBench-20...
Paper • Aug 11, 2025 • arXiv • Isabella R. Rossi, Kenji Sato, Nils Bergmann
The discovery of novel chemical compounds is traditionally hindered by the slow, iterative process of manual hypothesis generation and bench testing. We present ChemAgent, an Agentic AI framework t...
Paper • Jul 15, 2025 • arXiv • Kevin Zhu, Lara Croft, Julian Bao
Evaluating the long-horizon planning and adaptability of Agentic AI in the real world is fraught with safety and cost limitations. We establish Minecraft as the premier sandbox for open-ended agent...
Paper • Jun 21, 2025 • arXiv • Thomas K. V., Eleanor Rigby, M. Hasan
Traditional AI alignment techniques like RLHF are insufficient for Agentic AI, as autonomous systems frequently encounter novel edge cases in open-ended environments that were absent from their tra...
Paper • Mar 21, 2025 • arXiv • Albert Q. Jiang, Wenda Li, Szymon Tworkowski, Kuhu Syal
Automated theorem proving requires a blend of creative intuition and rigorous logical deduction, a combination that eludes pure deep learning models. We propose a Neurosymbolic Agentic AI framework...
Paper • Jul 21, 2025 • arXiv • Mohammad Azarijafari, Luisa Mich, Michele Missikoff
Artificial Intelligence agents represent the next major revolution in industrial automation. Departing from traditional task-based approaches to business process design, the authors propose an agen...
Paper • Aug 13, 2025 • arXiv • Hana Derouiche, Zaki Brahmi, Haithem Mazeni
The emergence of Agentic AI has ushered in a transformative paradigm where intelligent agents exhibit goal-directed autonomy, contextual reasoning, and dynamic multi-agent coordination. This paper ...
Paper • Dec 18, 2025 • arXiv • Anonymous Consortium
As agentic AI systems grow in capability and scope, adaptation becomes a central mechanism for improving performance, reliability, and generalization. This paper unifies the rapidly expanding resea...
Paper • Jun 21, 2016 • arXiv • Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, Dan Mané
Rapid progress in machine learning and artificial intelligence (AI) has brought increasing attention to the potential impacts of AI technologies on society. In this paper, we discuss one such poten...
Paper • May 9, 2023 • OpenAI • Steven Bills, Nick Cammarata, Dan Mossing, Henk Tillman, Leo Gao, Gabriel Goh, Ilya Sutskever, Jan Leike, Jeff Wu, William Saunders
Understanding the internal mechanisms of massive language models is a critical bottleneck for AI safety and alignment. Given the billions of parameters in modern models, manual human inspection of ...
Paper • Dec 16, 2021 • arXiv • Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, John Schulman
We introduce a method for fine-tuning language models to interact with a text-based web browser to answer open-ended questions. This model, WebGPT, searches the web, navigates through links, and sy...
Paper • Dec 13, 2019 • arXiv • Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemysław Dębiak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Chris Hesse, Ilya Sutskever, et al.
We present OpenAI Five, a system of five neural networks that learned to play the highly complex, imperfect-information esports game Dota 2 entirely through self-play. Dota 2 involves long time hor...
It ranks public content for cs.AI using recent discussion, review, and engagement signals so you can triage faster. This guidance is specific to cs.AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use weekly for fast-moving updates, monthly for stable trend confirmation, and all-time for evergreen references. This guidance is specific to cs.AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use the linked entities section to jump to labs, companies, and experts connected to this topic and explore their timelines. This guidance is specific to cs.AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Yes. Use the follow button on this page to subscribe and track new high-signal activity. This guidance is specific to cs.AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.