Frontier Models

Ask about this topic

Momentum

23 papers in the last four weeks, up 229% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 125

All topics
CardsList

  1. Finetuning with Sampling: SFT Learns Better Than You Think

    Oct 1, 2026Aayush Karan, Sitan Chen, Yilun DuSupervised FinetuningPost-Training

    Harvard University

  2. Growing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and Lean

    Sep 30, 2026Jules Viennot, Guillaume Baudart, Marc LelargeTheorem ProvingMath Problems

    IRIF, Universit´e Paris Cit´e, Inria, CNRS · DI ENS, PSL University, Inria

  3. Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools

    Sep 30, 2026Shijia Ge, Alex Zhou, Jianshu Zeng +12Robotic SystemsFrontier Models

    Hexafuture Inc. · Peking University · Beijing Institute of Technology +1

  4. DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?

    Sep 30, 2026Aditya Ramabadran, Simon Mahns, Tobias GesslerRecent Vision-Language ModelsMechanics

  5. When Context Changes: Understanding Update Failures in LLMs

    Sep 30, 2026Junyu Guo, Yuchen Fang, Shangding Gu +3Large Language Models FailGradient Staleness

    University of California, Berkeley

  6. Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning

    Sep 27, 2026Chenlong Yin, Xiaolong Jin, Wei Zou +2Attacker Large Language ModelRed-Teaming

    The Pennsylvania State University · Purdue University

  7. EnigmaForge: The Question Is Hidden in the Story

    Sep 24, 2026Daniel EisnerFrontier ModelsLanguage Model Computes

  8. Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes

    Sep 24, 2026Rahul Khedar, Mayank Malhotra, Avinash KarnFrontier ModelsDecisions

    PayPal AI

  9. Forecast Workflow Bench: Evaluating Language-Model Decisions with Budgeted Forecast Tools

    Sep 23, 2026Shunya NagashimaFrontier ModelsCapacity

    Neurogica Inc.

  10. Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

    Sep 22, 2026Xiaoyu Luo, Tao Ren, Wenrui Yu +3Frontier ModelsChain-of-Thought Reasoning

    Department of Computer Science Aalborg University, Copenhagen, Denmark · Department of Electronic Systems Aalborg University, Copenhagen, Denmark · Seafill

  11. Dual-Frontier: When Can an Agent Trust Its World Model?

    Sep 22, 2026Huatai Zhu, Qiang Chen, Ziqian Kou +5World ModelsCounterfactual Learning

    Central South University · The Hong Kong University of Science and Technology · Xiangjiang Laboratory +2

  12. Evaluating Decision Models for Text Annotation in Computational Social Science

    Sep 21, 2026Hazem Ibrahim, Yasir ZakiLarge Language Model AnnotationsComputational Social Science

    Computer Science, New York University Abu Dhabi, Abu Dhabi, UAE

  13. Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)

    Sep 21, 2026Amir Rafe, Subasish DasAccidentsCrashes

    Ingram School of Engineering, Texas State University, San Marcos, TX, USA

  14. this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent

    Sep 20, 2026Zehua Cheng, Wei Dai, Jiahao SunFrontier ModelsDecisions

    University of Oxford

  15. Alignment Forecasting: Predicting Misalignment From Training Data

    Sep 19, 2026Chen Yueh-Han, Bruce W. Lee, Ilia Sucholutsky +1Large Language Model AlignmentMisalignment Persona

    NYU, MATS · Independent · NYU +1

  16. Stress-testing Alignment Midtraining

    Sep 17, 2026Sid Baines, Jonathan Bostock, Maria Angelica Martinez +3Post-TrainingFrontier Models

    Arcadia Impact · Resolution

  17. Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry

    Sep 16, 2026Peter PotashFrontier ModelsInformation Asymmetry

  18. Do Frontier Models Seek Safety Evidence Before Acting?

    Sep 15, 2026Omer TafveezFrontier Models

    University of Michigan

  19. Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA

    Sep 14, 2026Luis M. SánchezModel AuditingConfabulation

    Toryx Inc.

  20. How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks

    Sep 14, 2026Ali Ansari, Haoran Sun, Andy Zeyi Liu +48Frontier ModelsLarge Language Model Benchmarks

  21. Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model Improvement

    Sep 12, 2026Shuxing Yang, Kaihao Zhu, Junjie Yang +13Frontier ModelsFrontiers

    College of Information Science and Electronic Engineering, Zhejiang University · Qiushi Engine Team

  22. TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards

    Sep 9, 2026Rui Sun, Zhan Shi, Bing HeReinforcement Learning With Verifiable RewardReasoning Traces

    Independent Researchers

  23. Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

    Sep 8, 2026Zongjie Li, Alan Z. W, John Nicolas J +4Agentic LearningFrontier Models

    Vera Praxis Lab

  24. GVS5H: Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance

    Aug 27, 2026Victor Gao, Vida Khosrowshahi, Ali Khosrowshahi +4Frontier ModelsTraining-Free

    Sang Won · Persis Capital Inc.

  25. Feature Priming in Online Linear Regression: Sparse-Regret Lower Bounds and Tight Coordinatewise Rates

    Aug 18, 2026Huibo Xu, Shi Fu, Qixin Zhang +1\Widetilde{\Mathcal{O}}(\Sqrt{T})$ RegretLower Bounds

    Nanyang Technological University, Singapore

  26. FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents

    Aug 12, 2026Yuhao Zhang, O. Ozan Koyluoglu, Thejas Venkatesh +4Finance BenchmarksFrontier Models

    Samaya AI

  27. Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence

    Aug 11, 2026Brian Wang, Bin Feng, Xiaoman Pan +26Artificial Intelligence EvaluationDiscovery

  28. Chartography: A Benchmark for Professional Chart Understanding

    Aug 11, 2026Suhaas Garre, Chris Mutty, Sushant Mehta +1ChartDiagnostic Benchmark

    Surge AI*

  29. Not a Monolith: Lab-Level Divergence in the Cooperative Equilibria of Chinese Frontier LLM Agents

    Aug 10, 2026Francisco León Zúñiga BolívarFrontier Large Language Model AgentsFrontier Models

    Institución Universitaria Colegio Mayor del Cauca · Popayán, Colombia

  30. Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?

    Aug 10, 2026Hui Xue, Fan YangSelf-Evolving AgentsPrompt Optimization

    Microsoft Research

  31. Business Arena: Benchmarking LLM Agents in a Realistic Marketplace

    Aug 9, 2026Yijun Pan, Yukun Lian, Kunyu Shi +5Large Language Model AgentsWebarena Domains

    1Accio Team, Alibaba Group · 2Yale University

  32. Memory--Batch Tradeoffs in Lipschitz Bandits

    Aug 8, 2026Zicheng Lyu, Zengfeng HuangContextual Bandit FrameworkInformation-Theoretic Limits

    Fudan University Shanghai, China · Fudan University Shanghai Innovation Institute Shanghai, China

  33. Ask-E: An Environment for Calibrated Question Generation

    Aug 7, 2026Sarah Pratt, Jae Sung Park, Scott Geng +1Faithful Question GenerationQuestion

    University of Washington · 2Allen Institute for AI

  34. From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models

    Aug 6, 2026Ali Jalal-KamaliFrontier ModelsSteering

    USC Institute for Creative Technologies

  35. Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay

    Aug 6, 2026Nossa IyamuReplayFrontier Models

    Independent Researcher

  36. SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models

    Aug 5, 2026Sihan Hu, Lyuhan Huang, Youjin Deng +1Frontier Models

    Hefei National Laboratory College of Mechanical and Electrical Engineering University of Science and Technology of China · Hefei National Laboratory Institute of Theoretical Physics University of Science and Technology of China Chinese Academy of Sciences Hefei 230026, China · Chinese Academy of Sciences Beijing 100190, China

  37. Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First

    Aug 5, 2026Ishaan Bhola, Adithyan Krishnan, Mukunda NSRepository-Level Code UnderstandingLarge Language Model Routing

    SuperAGI Research

  38. Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings

    Aug 5, 2026Agatha Duzan, Asa Cooper SticklandFrontier ModelsChain-of-Thought Reasoning

    EPFL · UK AI Security Institute

  39. The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals

    Aug 5, 2026Ruitong Li, Binjie Guo, Aisheng Mo +4Code QualityVerification Framework

    University of Hong Kong · Zhejiang University · Dalian University of Technology +1

  40. WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournament

    Aug 4, 2026Zhenran Wang, Zhonghan Bian, Jinsong Li +1Large Language Model ForecastingCompetition

  41. CurveShift: Is Agent Progress Scalar? Separating Level from Shape

    Jul 31, 2026Hanwen Xing, Pengyun Wang, BingXu Meng +8Agentic BenchmarksHard

    University of Southern California · University of Chicago · University of California, Berkeley +6

  42. Distilling Answer Set Programming Theories from Large Language Models

    Jul 30, 2026Nelson Higuera Ruiz, Markus Hofmarcher, Claudiu Leoveanu-CondreiAnswer Set ProgrammingNeuro-Symbolic Framework

    ExtensityAI, Vienna, Austria

  43. Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control

    Jul 30, 2026Takumi Shioda, Kohei Terashima, Tatsuo NagaiHvac ControlReinforcement Fine-Tuning

    The University of Tokyo · Tokyo University of Science

  44. Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks

    Jul 29, 2026Jeff Mohl, Nelson Gardner-Challis, Magda Dubois +6Model AuditingAgentic Benchmarks

    Independent · UK AI Security Institute · MARS +4

  45. Dimensionality and Measurement Precision in HLE's Multiple-Choice Subset

    Jul 29, 2026Mayank Sharma, Savira Nadela, Tyler MattesonFrontier ModelsAssessment

    Stanford University

  46. APEX-Accounting

    Jul 29, 2026Julien Benchek, Austin Bennett, Jasmin Kern +8Frontier ModelsToken Budget Allocation

    1Mercor · 2Ramp

  47. HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models

    Jul 29, 2026Petr Simecek, Elnaz Babayeva, Jiri Balhar +23Common Vulnerabilities And ExposureOpen-Source

    AISLE, San Francisco, CA, USA and Prague, Czech Republic · Central European Institute of Technology, Masaryk University, Brno, Czech Republic

  48. A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever

    Jul 26, 2026Sietse SchelpeFrontier ModelsLanguage Model Computes

    Corbenic AI

  49. Confidently Wrong: Exception Chain Collapse in Frontier LLM Rule Evaluation

    Jul 25, 2026Paul Simpson, John Kozak, Lisa DoakeFrontier ModelsLarge Language Model Evaluation

    Aethis (aethis.ai)

  50. Search-on-Graph-R1: Training Large Language Models to Search Knowledge Graphs with Reinforcement Learning

    Jul 20, 2026Jia Ao Sun, Hao Yu, Fengran Mo +4Knowledge GraphsSparql

    Université de Montréal · Mila – Québec AI Institute · McGill University +2

  51. FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches

    Jul 20, 2026Jiacheng Ding, Cong Guo, Jason XuLarge Language Model ForecastingBetting

    University of Memphis Memphis, Tennessee, USA · QuantaInsight Seattle, Washington, USA

  52. Safety That Does Not Transfer: Cross-Lingual Clinical Correctness Drift in Deployable Medical Language Models

    Jul 19, 2026Anthonio Oladimeji Gabriel, Dimeji Olawuyi, Toba Ajayi +1Multilingual SafetyCross-Lingual Consistency

    AI SafetyX

  53. Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent

    Jul 19, 2026Arunabh DastidarVerification FrameworkConfabulation

    for the Leni Team · Leni Inc.

  54. Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning

    Jul 17, 2026Ajay Patel, Kartik Hosanagar, Ramayya Krishnan +2Artificial Intelligence BenchmarksHuman-Annotated Benchmark

    Operations, Information and Decisions Department, The Wharton School, University of Pennsylvania, Philadelphia, 19104, PA, USA · Heinz College of Information Systems and Public Policy, Carnegie Mellon University, Pittsburgh, 15213, PA, USA · Department of Computer and Information Science, University of Pennsylvania, Philadelphia, 19104, PA, USA +1

  55. Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors

    Jul 15, 2026Michael O. EnioladeSecurity EvaluationArtificial Intelligence Risk

    University of the Cumberlands

  56. The Model Knows Your Project, Not You: Measuring Recognition in LLMs with NameRank

    Jul 14, 2026Bojie Li, Noah ShiCredibilityFrontier Models

    Pine AI · University of Washington

  57. Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs

    Jul 13, 2026Sheng-Wei Peng, Yi-Hsun Lin, Yi-Pei LeeCoding AgentsCode Optimization

    Pegatron Corporation Taipei, Taiwan

  58. From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Under Delayed Ground Truth

    Jul 13, 2026Aleh ManchuliantsauData-Driven ForecastingUncertainty Score

    Independent Researcher

  59. Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention

    Jul 10, 2026Siddharth Pal, Viktoria RojkovaRecurrent StateCache

  60. Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution

    Jul 9, 2026Ethan Leung, Elias Lumer, Corey Feld +3Large Language Model JudgesCitations

    Commercial Technology and Innovation Office, PricewaterhouseCoopers, U.S.