Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages; model links come from model cards citing the paper.

1,189 papers

Papers
TitleAuthorsOrganizationPublishedIntroduces Models (and artifacts) whose model card or documentation cites this paper — inbound described_by relations.DatasetsBenchmarksCode
Emergent Risks in Generative Multi-Agent SystemsarXiv:2603.27771cs.MAYue Huang, Yu Jiang, Wenjie Wang +211 Sept 2026
MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math TeachersarXiv:2604.04036cs.IRZhihan Guo, Yuting Lu, Jionghao Lin11 Sept 2026
Formalizing building-up constructions of self-dual codes through isotropic lines in LeanarXiv:2604.08485cs.ITJae-Hyun Baek, Jon-Lark Kim11 Sept 2026
LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial DomainsarXiv:2604.16379cs.IRRyogo Hishikawa, Ichiro Kataoka, Shinya Yuda11 Sept 2026
Strategic Type SpacesarXiv:2606.08297econ.THOlivier Gossner, Rafael Veiel11 Sept 2026
A Group-Based Resource Allocation Model for the Fractional Knapsack ProblemarXiv:2609.06470cs.DSAbhinaba Chakraborty11 Sept 2026
OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist WorkflowsarXiv:2609.09203cs.AIAayam Bansal, Keertan Balaji11 Sept 2026
Adaptive Entangled Game Modules in Artificial General IntelligencearXiv:2609.09226cs.AIHaochen Li, Xinshuai Guo, Jingdong Ouyang +211 Sept 2026
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic TasksarXiv:2609.09233cs.AIWasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth +211 Sept 2026
Gradland: On Phenomenal Experience, Differentiated Across Many DimensionsarXiv:2609.09306cs.AIDavid Balduzzi11 Sept 2026
An Autonomous GeoAI Agent for Arctic Eco-NavigationarXiv:2609.09374cs.AISamira Alkaee Taleghan, Younghyun Koo, Farnoush Banaei-Kashani11 Sept 2026
The Menu Is an Execution Prior: State-Path Tool Menus for Online AgentsarXiv:2609.09395cs.AIBo Yan, Weikai Lin, Song Wang11 Sept 2026
Decision-Focused Active Learning for Scale-Aware Critical-Materials RecoveryarXiv:2609.09413cs.AINiranjan Srinivas, Debajyoti Ray, Elias Nakouzi11 Sept 2026
Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model ExplorationarXiv:2609.09418cs.AIYiran Qiao, Feng Wang, Jing Ma11 Sept 2026
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?arXiv:2609.09428cs.AIYanfei Hu Fleischhauer, Alona Zharova, Nadja Klein +111 Sept 2026
Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal RepresentationsarXiv:2609.09448cs.AIPriyanka Mary Mammen, Emil Joswin, Srujananjali Medicherla11 Sept 2026
ContractEval: Query-Conditioned Execution Matching for Procedural Instruction ConformancearXiv:2609.09458cs.AIPraphul Singh, Shanu Kumar, Akshat Agarwal +111 Sept 2026
Multi-Agent Agentic Graph Learning via Structural SignaturesarXiv:2609.09565cs.AILiang Qu, Jianxin Li, Hua Wang11 Sept 2026
CityPlanner: A Sandbox Agent for Executable Urban PlanningarXiv:2609.09578cs.AIWentao Zhang, Jingyuan Wang, Zetong Zhou +211 Sept 2026
A Function-Space Approach to the Statistical Mechanics of Learning DynamicsarXiv:2609.09589cs.AIYizhou Zhang, Weichen Wu, Lun Du +111 Sept 2026
From State Synchronization to Cognitive Self-Evolution: An Operational Architecture for Cognitive Digital TwinsarXiv:2609.09625cs.AIHaoran Gao, An Li, Zhen Li +111 Sept 2026
Seven Sources of Physical AI Capability FormationarXiv:2609.09627cs.AIGang Chen11 Sept 2026
RobustSGPO: Search-Space Control for Agent Harness EvolutionarXiv:2609.09646cs.AIZibo Zhao, Jijun Shi, Mo Zhou +211 Sept 2026
Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk DiscoveryarXiv:2609.09647cs.AIDivyanshu Kumar, Nitin Aravind Birur, Tanay Baswa +211 Sept 2026
RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation SystemsarXiv:2609.09657cs.AIHaichuan Hu, Yang Xiao, Mingni Tang +211 Sept 2026

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Linked models, datasets, benchmarks and code come from stated relations only; a dash means no source stated one.