Key papers

• ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes (2026)
  Qihao Zhao et al.
  12.62
• A global predicted-fMRI drive signal from TRIBE does not predict YouTube replay heatmaps (2026)
  Barada Sahu et al.
  7.37
• How Far Are We From True Auto-Research? (2026)
  Zhengxin Zhang et al.
  6.64
• Towards an automated AI-based framework for floor plan compliance checks for residential buildings (2026)
  Subash Gautam et al.
  5.01
• Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine (2026)
  Aureka AI OpenDDE project
  5.01
• UzWordnet and Generative AI for Learning Uzbek by Game Playing (2026)
  Alessandro Agostini et al.
  5.01
• SCALE: Self-Supervised Constraint-Aware Layout GEneration for Local P&R DRV Fixing at Advanced Nodes (2026)
  Chia-Tung Ho et al.
  5.01
• Generative Ontology Induction: Domain-Agnostic Schema Discovery from Document Corpora Using Large Language Models (2026)
  Sergei Sergienko
  4.39
• TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complex (2026)
  Yuliang Yan et al.
  4.39
• A Multi-Level Architecture for Reusable Materials Ontologies -- The OntoCrafter Ceramics Ontology (OCO) as Reference Implementation (2026)
  Thomas Pannek et al.
  4.33
• AXLE: A Cloud Infrastructure for Lean 4 Theorem Proving Utilities (2026)
  Jimmy Xin et al.
  4.33
• PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies (2026)
  Ahmad Yehia et al.
  4.27
• Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development (2026)
  Christopher Koch
  4.27
• Quality and Security Signals in AI-Generated Python Refactoring Pull Requests (2026)
  Mohamed Almukhtar et al.
  4.27
• LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation (2026)
  Jiabei Xiao et al.
  4.27
• Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains (2026)
  Elias Calboreanu
  4.27
• HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML (2026)
  Jiajun Wu et al.
  4.27
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses (2026)
  Jiahang Lin et al.
  4.09
• Natural-Language Agent Harnesses (2026)
  Linyue Pan et al.
  4.04
• Swe-dev: Evaluating And Training Autonomous Feature-driven Software Development (2025)
  Yaxin Du, Yuzhu Cai, Yifan Zhou, et al.
  3.76
• Capability-driven Skill Generation With Llms: A Rag-based Approach For Reusing Existing Libraries And Interfaces (2025)
  Luis Miguel Vieira da Silva, Aljosha Köcher, Nicolas König, et al.
  3.75
• TusoAI: Agentic Optimization for Scientific Methods (2026)
  Alistair Turcan et al.
  3.70
• SIADAFIX: Issue Description Response For Adaptive Program Repair (2025)
  Xin Cao, Nan Yu
  3.57
• Understanding Agent-Based Patching of Compiler Missed Optimizations (2026)
  Batu Guan et al.
  3.51
• FOI-O: A global ontology and verification framework for Freedom of Information process modelling (2026)
  Dylan A Mordaunt
  3.51
• Specification Grounding Drives Test Effectiveness for LLM Code (2026)
  Amin Haeri et al.
  3.51
• ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions To Structured Prompts Via Principle-based Optimization (2025)
  Seungyoun Yi, Minsoo Khang, Sungrae Park
  2.55
• LEGO: An LLM Skill-Based Front-End Design Generation Platform (2026)
  Jincheng Lou et al.
  1.94
• ContractBench: Can LLM Agents Preserve Observation Contracts? (2026)
  Jicheng Wang et al.
  1.94
• VeriPilot: An LLM-Powered Verilog Debugging Framework (2026)
  Yihan Wang et al.
  1.94
• The AI Codebase Maturity Model: From Assisted Coding To Fully Autonomous Systems (2026)
  Andy Anderson
  1.94
• RESCORE: Llm-driven Simulation Recovery In Control Systems Research Papers (2026)
  Vineet Bhat, Shiqing Wei, Ali Umut Kaypak, et al.
  1.94
• Composer 2 Technical Report (2026)
  Cursor Research, :, Aaron Chan, et al.
  1.94
• From Correctness to Collaboration: A Human-Centered Taxonomy of AI Agent Behavior in Software Engineering (2026)
  Tao Dong et al.
  1.94
• HCAG: Hierarchical Abstraction And Retrieval-augmented Generation On Theoretical Repositories With Llms (2026)
  Yusen Wu, Xiaotie Deng
  1.94
• CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging (2026)
  Shiyang Li et al.
  1.89
• Given, When, Then, Again: Mining Subscenario Refactoring Candidates in Behaviour-Driven Test Suites with ML Classifiers and LLM-Judge Baselines (2026)
  Ali Hassaan Mughal et al.
  1.89
• PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control (2026)
  Jingxuan Wei et al.
  1.89
• paper.json: A Coordination Convention for LLM-Agent-Actionable Papers (2026)
  Arquimedes Canedo
  1.89
• Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports (2026)
  Mahmut Furkan Gon et al.
  1.89
• More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries (2026)
  Hongwen Song et al.
  1.89
• PPO Guided Agentic Pipeline For Adaptive Prompt Selection And Test Case Generation (2026)
  Gourisetty Venkata Sai Koushik, Dama Aditya, Mahankali Harish Sai, et al.
  1.89
• Towards Predicting Multi-Vulnerability Attack Chains in Software Supply Chains from Software Bill of Materials Graphs (2026)
  Laura Baird et al.
  1.83
• The Last Human-Written Paper: Agent-Native Research Artifacts (2026)
  Jiachen Liu et al.
  1.83
• Skvm: Revisiting Language VM For Skills Across Heterogenous Llms And Harnesses (2026)
  Le Chen, Erhu Feng, Yubin Xia, et al.
  1.83
• Adaexplore: Failure-driven Adaptation And Diversity-preserving Search For Efficient Kernel Generation (2026)
  Weihua Du, Jingming Zhuo, Yixin Dong, et al.
  1.83
• From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning (2026)
  Omer Nacar et al.
  1.78
• SciNav: A General Agent Framework for Scientific Coding Tasks (2026)
  Tianshu Zhang et al.
  1.78
• Reachability Across the NL/PL Boundary: A Taxonomy-Driven Dataflow Model for LLM-Integrated Applications (2026)
  Zihao Xu et al.
  1.78
• Design-os: A Specification-driven Framework For Engineering System Design With A Control-systems Design Case (2026)
  H. Sinan Bank, Daniel R. Herber, Thomas H. Bradley
  1.78
• Quality-driven Agentic Reasoning For Llm-assisted Software Design: Questions-of-thoughts (qot) As A Time-series Self-qa Chain (2026)
  Yen-Ku Liu, Yun-Cheng Tsai
  1.78
• Monte Carlo Tree Search for Execution-Guided Program Repair with Large Language Models (2026)
  Yixuan Liang
  1.72
• Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study (2026)
  Khairul Alam et al.
  1.72
• A Dual-Loop Agent Framework for Automated Vulnerability Reproduction (2026)
  Bin Liu et al.
  1.72
• Agile V: A Compliance-ready Framework For Ai-augmented Engineering -- From Concept To Audit-ready Delivery (2026)
  Christopher Koch, Joshua Andreas Wellbrock
  1.72
• Semantic Laundering in AI Agent Architectures: Why Tool Boundaries Do Not Confer Epistemic Warrant (2026)
  Oleg Romanchuk et al.
  1.67
• VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution (2026)
  Mingming Zhang et al.
  1.67
• DUET: Agentic Design Understanding Via Experimentation And Testing (2025)
  Gus Henry Smith, Sandesh Adhikary, Vineet Thumuluri, et al.
  1.61
• VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization (2025)
  Youpeng Li et al.
  1.56
• Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs (2026)
  Yunhao Chen et al.
  1.56