Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages.

1,047 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation RerankingarXiv:2609.00588Guangyu Chen, Boxuan Lyu, Hidetaka Kamigaito +211 Sept 2026cs.CL—89
OUTLETS: Output-Length Prediction from Speculative Decoding BackbonesarXiv:2609.01068Weihuang Wen, Yingying Liu, Yichuan Liu +211 Sept 2026cs.CL—89
Cache-Aware Joint Router Adaptation for Memory-Efficient MoE InferencearXiv:2609.04895Zhenhe Wu, Yaping Jin, Qinghua Xing +211 Sept 2026cs.CL—89
Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity LinkingarXiv:2609.07379Tien Nam Nguyen, Emanuela Boros, Ahmed Hamdi +211 Sept 2026cs.CL—89
Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise JudgementsarXiv:2609.09425Oliver G. B. Garrod, Robin A. A. Ince, Meng Liu +211 Sept 2026cs.CL—89
CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn PrescriptionarXiv:2609.09766Minjoo Kim, Sangjin Park, Seung Hwan Cho11 Sept 2026cs.CL—89
SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better TeachersarXiv:2609.09999Xixian Liao, Maite Melero11 Sept 2026cs.CL—89
Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)arXiv:2601.15397Peidong Wang, Jian Xue, Jinyu Li11 Sept 2026cs.AI—89
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory SynthesisarXiv:2603.20278Zhuofeng Li, Dongfu Jiang, Xueguang Ma +211 Sept 2026cs.IR—89
Emergent Risks in Generative Multi-Agent SystemsarXiv:2603.27771Yue Huang, Yu Jiang, Wenjie Wang +211 Sept 2026cs.MA—89
MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math TeachersarXiv:2604.04036Zhihan Guo, Yuting Lu, Jionghao Lin11 Sept 2026cs.IR—89
Formalizing building-up constructions of self-dual codes through isotropic lines in LeanarXiv:2604.08485Jae-Hyun Baek, Jon-Lark Kim11 Sept 2026cs.IT—89
Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor UnderstandingarXiv:2604.15210Hatice Merve Vural, Doga Kukul, Ege Erdem Ozlu +211 Sept 2026cs.AI—89
LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial DomainsarXiv:2604.16379Ryogo Hishikawa, Ichiro Kataoka, Shinya Yuda11 Sept 2026cs.IR—89
Strategic Type SpacesarXiv:2606.08297Olivier Gossner, Rafael Veiel11 Sept 2026econ.TH—89
Cognitive Digital Twins: Ethical Risks and Governance for AI Systems That Model the MindarXiv:2606.23094Vamshi Krishna Bonagiri, Juan Nicolas Sepulveda-Arias, Abdoul Jalil Djiberou Mahamadou +111 Sept 2026cs.AI—89
LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned DistributionarXiv:2606.28335Adib Sakhawat, Syed Rifat Raiyan, Tahsin Islam +211 Sept 2026cs.CY—89
Efficient Adaptation of LLMs for Hate Speech Detection in Low-Resource Languages: A Comparative Study on Roman UrduarXiv:2608.18142Toneema Zubair, Muhammad Junaid Asif, Faisal Kamiran +211 Sept 2026cs.AI—89
Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM SystemsarXiv:2609.00237Rakibul Hasan Rajib, Mengxin Zheng, Qian Lou11 Sept 2026cs.AI—89
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic EvaluationarXiv:2609.04298Lin Shi (Audrey), Haowei Lin (Audrey), Zixuan Zhu (Audrey) +211 Sept 2026cs.AI—89
A Group-Based Resource Allocation Model for the Fractional Knapsack ProblemarXiv:2609.06470Abhinaba Chakraborty11 Sept 2026cs.DS—89
OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist WorkflowsarXiv:2609.09203Aayam Bansal, Keertan Balaji11 Sept 2026cs.AI—89
Adaptive Entangled Game Modules in Artificial General IntelligencearXiv:2609.09226Haochen Li, Xinshuai Guo, Jingdong Ouyang +211 Sept 2026cs.AI—89
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic TasksarXiv:2609.09233Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth +211 Sept 2026cs.AI—89
Gradland: On Phenomenal Experience, Differentiated Across Many DimensionsarXiv:2609.09306David Balduzzi11 Sept 2026cs.AI—89
An Autonomous GeoAI Agent for Arctic Eco-NavigationarXiv:2609.09374Samira Alkaee Taleghan, Younghyun Koo, Farnoush Banaei-Kashani11 Sept 2026cs.AI—89
The Menu Is an Execution Prior: State-Path Tool Menus for Online AgentsarXiv:2609.09395Bo Yan, Weikai Lin, Song Wang11 Sept 2026cs.AI—89
Decision-Focused Active Learning for Scale-Aware Critical-Materials RecoveryarXiv:2609.09413Niranjan Srinivas, Debajyoti Ray, Elias Nakouzi11 Sept 2026cs.AI—89
Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model ExplorationarXiv:2609.09418Yiran Qiao, Feng Wang, Jing Ma11 Sept 2026cs.AI—89
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?arXiv:2609.09428Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein +111 Sept 2026cs.AI—89
Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal RepresentationsarXiv:2609.09448Priyanka Mary Mammen, Emil Joswin, Srujananjali Medicherla11 Sept 2026cs.AI—89
ContractEval: Query-Conditioned Execution Matching for Procedural Instruction ConformancearXiv:2609.09458Praphul Singh, Shanu Kumar, Akshat Agarwal +111 Sept 2026cs.AI—89
Multi-Agent Agentic Graph Learning via Structural SignaturesarXiv:2609.09565Liang Qu, Jianxin Li, Hua Wang11 Sept 2026cs.AI—89
CityPlanner: A Sandbox Agent for Executable Urban PlanningarXiv:2609.09578Wentao Zhang, Jingyuan Wang, Zetong Zhou +211 Sept 2026cs.AI—89
A Function-Space Approach to the Statistical Mechanics of Learning DynamicsarXiv:2609.09589Yizhou Zhang, Weichen Wu, Lun Du +111 Sept 2026cs.AI—89
From State Synchronization to Cognitive Self-Evolution: An Operational Architecture for Cognitive Digital TwinsarXiv:2609.09625Haoran Gao, An Li, Zhen Li +111 Sept 2026cs.AI—89
Seven Sources of Physical AI Capability FormationarXiv:2609.09627Gang Chen11 Sept 2026cs.AI—89
RobustSGPO: Search-Space Control for Agent Harness EvolutionarXiv:2609.09646Zibo Zhao, Jijun Shi, Mo Zhou +211 Sept 2026cs.AI—89
Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk DiscoveryarXiv:2609.09647Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa +211 Sept 2026cs.AI—89
RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation SystemsarXiv:2609.09657Haichuan Hu, Yang Xiao, Mingni Tang +211 Sept 2026cs.AI—89

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Each paper page shows the abstract, related models and every source snapshot.