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.
  10.72
• LLM Collaboration With Multi-Agent Reinforcement Learning (2025)
  Shuo Liu et al.
  8.89
• ReCode: Reinforcing Code Generation with Reasoning-Process Rewards (2025)
  Lishui Fan et al.
  8.61
• Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning (2025)
  Alexander Golubev et al.
  8.51
• IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests (2026)
  Ankur Singh et al.
  5.01
• A Role-Based Multi-Agent Model for Climate Adaptation Deliberation Across Living Labs (2026)
  \"Onder G\"urcan 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
• SmartHomeSecure: Automated Detection and Repair of Smart Home Configuration Errors Using Large Language Models (2026)
  Yizhi Wang et al.
  4.39
• Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1 (2026)
  Kabir Moghe et al.
  4.39
• Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video (2026)
  Mayur Kurup et al.
  4.39
• What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study (2026)
  Robert Richardson
  4.39
• The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI (2026)
  Muayad Sayed Ali et al.
  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
• Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents (2026)
  Harry Owiredu-Ashley
  4.39
• Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows (2026)
  Wei-Jung Huang
  4.39
• The Patchwork Problem in LLM-Generated Code (2026)
  Viraaji Mothukuri et al.
  4.39
• Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills (2026)
  Jialun Cao et al.
  4.39
• Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability (2026)
  Shirley Yu et al.
  4.39
• The Hitchhiker's Guide to Monoculture (2026)
  Gordon Burtch
  4.39
• Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop Framework (2026)
  Aditya Aggarwal et al.
  4.39
• Faithful Autoformalization of Natural Language Assertions (2026)
  Hongyi Liu et al.
  4.39
• Early Adoption of Agentic Coding Tools by GitHub Projects (2026)
  Maliha Noushin Raida et al.
  4.39
• Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre-Response Governance (2026)
  Ali Toygar Abak
  4.39
• ExecuGraph: A Multi-Agent, Execution-Grounded Framework for Reliable Backend Code Synthesis with Large Language Models (2026)
  Sai Deekshith Lekkala et al.
  4.39
• StrideDiffusion: Accelerating Diffusion Models for Time-series Generation (2026)
  Du Yin et al.
  4.39
• HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices (2026)
  Wei Liu et al.
  4.39
• Encoding Event-B Proof Rules in Prolog: An Interactive Sequent Prover for ProB (2026)
  Katharina Engels (Heinrich Heine University D\"usseldorf) et al.
  4.39
• Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards (2026)
  Erfan Aghadavoodi Jolfaei et al.
  4.27
• ACECODER: Acing Coder RL via Automated Test-Case Synthesis (2025)
  Huaye Zeng et al.
  4.25
• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning (2025)
  Lakshya A Agrawal et al.
  3.99
• TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning (2025)
  Hongyu Lin et al.
  3.92
• Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving (2025)
  Daoguang Zan and Zhirong Huang and Wei Liu and Hanwu Chen and Linhao Zhang and Shulin Xin and Lu Chen and Qi Liu and Xiaojian Zhong and Aoyan Li and Siyao Liu and Yongsheng Xiao and Liangqiang Chen and Yuyu Zhang and Jing Su and Tianyu Liu and Rui Long and Kai Shen and Liang Xiang
  3.70
• SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution (2025)
  Yuxiang Wei et al.
  3.59
• Cross-site scripting adversarial attacks based on deep reinforcement learning: Evaluation and extension study (2025)
  Samuele Pasini et al.
  3.59
• Specification Grounding Drives Test Effectiveness for LLM Code (2026)
  Amin Haeri et al.
  3.51
• Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks? (2026)
  Spandan Garg et al.
  3.39
• Automating Formal Verification with Reinforcement Learning and Recursive Inference (2026)
  Max Tan
  3.39
• Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning (2025)
  Jia Fu et al.
  2.99
• Learning to Generate Unit Test via Adversarial Reinforcement Learning (2025)
  Dongjun Lee et al.
  2.99
• Kevin: Multi-Turn RL for Generating CUDA Kernels (2025)
  Carlo Baronio et al.
  2.93
• Process-Supervised Reinforcement Learning for Code Generation (2025)
  Yufan Ye et al.
  2.65
• Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild (2026)
  Hong Yi Lin et al.
  2.00
• Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality (2026)
  Oussama Ben Sghaier et al.
  2.00
• Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning (2026)
  Shouyu Yin et al.
  1.89
• PPO guided Agentic Pipeline for Adaptive Prompt Selection and Test Case Generation (2026)
  Gourisetty Venkata Sai Koushik and Dama Aditya and Mahankali Harish Sai and Peddi Siddarhta and Shadab Ahmad and Vivek Yelleti
  1.89
• Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture (2026)
  Mehmet Iscan
  1.89
• Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation (2026)
  Xin-Ye Li et al.
  1.89
• Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning (2026)
  Lingzhe Zhang et al.
  1.89
• Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs (2026)
  Yujia Chen et al.
  1.89
• BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models (2026)
  Yuanhao Li et al.
  1.89
• CA2: Code-Aware Agent for Automated Game Testing (2026)
  Valliappan Chidambaram Adaikkappan et al.
  1.89
• Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation (2026)
  Shuyin Ouyang et al.
  1.89
• OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems (2026)
  Kun Liu et al.
  1.83
• WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning (2026)
  Juyong Jiang et al.
  1.83
• MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning (2026)
  Sicheng Zhu et al.
  1.78
• ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning (2026)
  Juyong Jiang et al.
  1.78
• A Reference Architecture of Reinforcement Learning Frameworks (2026)
  Xiaoran Liu et al.
  1.78
• Automatic Generation of High-Performance RL Environments (2026)
  Seth Karten and Rahul Dev Appapogu and Chi Jin
  1.78