Key papers

• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities (2026)
  Zichen Ding et al.
  12.26
• Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable (2026)
  Ruhan Wang et al.
  10.93
• OpenForgeRL: Train Harness-native Agents in Any Environment (2026)
  Xiao Yu et al.
  8.86
• FilmBench: A Film-Grade Benchmark for Cinematic Video Generation (2026)
  Shengyi Wang et al.
  8.24
• NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs (2026)
  Jiarong Zhao et al.
  7.96
• Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code (2026)
  Niels M\"undler-Sasahara et al.
  7.69
• IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation (2026)
  Varun Gumma et al.
  7.37
• OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding (2026)
  Jingbo Zhou et al.
  5.46
• FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills (2026)
  Zeyu Ren et al.
  5.01
• Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images (2026)
  Ronak Bhalgami
  5.01
• Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks (2026)
  Michael Kouremetis et al.
  5.01
• ToolGuardian: Declarative Security for AI Agent-Tool Interactions (2026)
  Arun Ravindran et al.
  5.01
• CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference (2026)
  Jiyuan Tan et al.
  5.01
• Comparing Large Language Models on Scrum Certification-Style Questions: Accuracy, Stability, and Error Patterns (2026)
  Robson Alves Vilar et al.
  4.39
• HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing (2026)
  Ya Wang et al.
  4.39
• Reliable and Developer-Aligned Evaluation of Agents for Software Engineering (2026)
  Razvan Mihai Popescu
  4.39
• What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study (2026)
  Robert Richardson
  4.39
• Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents (2026)
  Vikas Reddy et al.
  4.39
• The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents (2026)
  Xing Zhang et al.
  4.39
• Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows (2026)
  Wei-Jung Huang
  4.39
• SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents (2026)
  Tianming Sha et al.
  4.39
• FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents (2026)
  Srihari Unnikrishnan et al.
  4.39
• Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants (2026)
  Dipesh Tharu Mahato
  4.39
• LessonBench-V1: A Benchmark Dataset for Evaluating AI Lesson Generation Agents (2026)
  Ravidu Suien Rammuni Silva et al.
  4.39
• The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI (2026)
  Anubhab Banerjee
  4.39
• Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution (2026)
  Hironao Nakamura
  4.39
• Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes (2026)
  Hiroki Tamba
  4.39
• Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows (2026)
  Keyur Gabani
  4.39
• Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs (2026)
  Sheng-Wei Peng et al.
  4.39
• Baselines Before Architecture: Evaluating Coding Agents for Autonomous Penetration Testing (2026)
  Ananda Dhakal et al.
  4.39
• Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop Framework (2026)
  Aditya Aggarwal et al.
  4.39
• Analyzing Curricular Pattern Complexity Using AI to Improve On-Time Graduation Rates (2026)
  Lynn Vonderhaar et al.
  4.39
• SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests (2026)
  Maha Ayub et al.
  4.39
• RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar (2026)
  Marek \v{S}uppa et al.
  4.39
• EZSMT Version 3, Matured (2026)
  Yuliya Lierler
  4.39
• The Refusal Residue: When Probes Catch Alignment Faking and When They Don't (2026)
  Aman Mehta
  4.39
• Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of an Agentic AI Tutoring System (2026)
  Teri Rumble et al.
  4.39
• The Caf\'e in Amsterdam: When the Incumbent Becomes the Oracle (2026)
  Augusto Camargo
  4.39
• Set-shifting Behavioral Test for Harnessed Agents (2026)
  Ziwei Ye
  4.39
• Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors (2026)
  Michael O. Eniolade
  4.39
• DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments (2026)
  Huatao Li et al.
  4.39
• Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 (2026)
  Wenxiao Wang et al.
  4.39
• Early Adoption of Agentic Coding Tools by GitHub Projects (2026)
  Maliha Noushin Raida et al.
  4.39
• Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning (2026)
  Chih-Hsuan Yang et al.
  4.39
• AgentFAIR: A Multi-Agent Collaborative Framework for FAIRness Evaluation of Geospatial Datasets (2026)
  Ming Chen et al.
  4.39
• Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre-Response Governance (2026)
  Ali Toygar Abak
  4.39
• Binding Drift in Multi-Step Tool-Augmented Agents (2026)
  Rahul Suresh Babu et al.
  4.39
• CODENS: Transforming Code Changes into Living, Accessible, and Queryable Documentation (2026)
  Abdelhak Kelious et al.
  4.39
• Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts (2026)
  Haodi Fan et al.
  4.39
• SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation (2026)
  Weifeng Sun et al.
  4.39
• DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making (2026)
  Raffi Khatchadourian
  4.39
• From Obligation to Specification: A Survey on Validating EU AI Act Requirements in RE (2026)
  T. Y. Emmy Lai et al.
  4.39
• Cloud-Native Evaluation-as-a-Service: A Microservices Architecture for Scalable AI Monitoring with Conformal Guarantees (2026)
  Lei Yang
  4.39
• Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code (2026)
  Vidyut Sriram et al.
  4.39
• Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa? (2026)
  Zuodong Xiang et al.
  4.39
• What AI Red-Team Evaluations Can and Cannot Prove (2026)
  Bandana Kaur
  4.39
• Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting (2026)
  Denis Mayr Lima Martins et al.
  4.39
• Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning (2026)
  Shujin Wu et al.
  4.39
• CEL: Comprehensive Counterfactual Explanations Library and Benchmark (2026)
  Oleksii Furman et al.
  4.39
• Benchmarking Text-to-SQL under Role-Based Access Control (2026)
  Yang Fei et al.
  4.39