mlsanityData to 7 Oct 2026

GLM-5: from Vibe Coding to Agentic Engineering

arXiv 2602.15763 ↗First posted 17 Feb 2026cs.LG cs.CLcited by 502

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

Key facts. Cited by 502 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 45 of its 62 references that are in the map. First posted on arXiv 17 Feb 2026.

Builds on

45 of 62 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents26 May
  2. 2025SWE-smith: Scaling Data for Software Engineering Agents30 Apr

Other references · 43

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  6. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  7. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  8. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  9. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  10. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  11. 2025Group Sequence Policy Optimizationcited by 788
  12. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
31 more
  1. 2021Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LMcited by 621
  2. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  3. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 598
  4. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
  5. 2024Gated Delta Networks: Improving Mamba2 with Delta Rulecited by 483
  6. 2026Kimi K2.5: Visual Agentic Intelligencecited by 449
  7. 2015Policy Distillationcited by 414
  8. 2024DataComp-LM: In search of the next generation of training sets for language modelscited by 381
  9. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
  10. 2024Measuring short-form factuality in large language modelscited by 345
  11. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 344
  12. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 171
  13. 2025AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning datasetcited by 165
  14. 2023TACO: Topics in Algorithmic COde generation datasetcited by 150
  15. 2025GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Taskscited by 142
  16. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 139
  17. 2024HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughlycited by 119
  18. 2025Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agentscited by 75
  19. 2025SWE-bench Goes Live!cited by 74
  20. 2025The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Executioncited by 73
  21. 2025Towards Robust Mathematical Reasoningcited by 67
  22. 2025Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Modelcited by 50
  23. 2026MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Serverscited by 46
  24. 2023Zero Bubble Pipeline Parallelismcited by 39
  25. 2025Jet-Nemotron: Efficient Language Model with Post Neural Architecture Searchcited by 39
  26. 2025Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architecturescited by 38
  27. 2024RepoQA: Evaluating Long Context Code Understandingcited by 35
  28. 2025Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervisioncited by 22
  29. 2024FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelismcited by 19
  30. 2026Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluationcited by 6
  31. 2025EntropyLong: Effective Long-Context Training via Predictive Uncertaintycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 502.

502 papers.

Sort:

By area:

  1. 2026Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipecited by 262
  2. 2026Gemma 4 Technical Reportcited by 187
  3. 2026Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixescited by 122
  4. 2026Kimi K3: Open Frontier Intelligencecited by 99
  5. 2026Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agentscited by 57
  6. 2026SkillNet: Create, Evaluate, and Connect AI Skillscited by 48
  7. 2026Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipecited by 43
  8. 2026RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillationcited by 33
  9. 2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Datacited by 32
  10. 2026Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 32
  11. 2026GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agentscited by 30
  12. 2026Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Levelcited by 29
38 more
  1. 2026Flow-OPD: On-Policy Distillation for Flow Matching Modelscited by 29
  2. 2026WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluationcited by 29
  3. 2026MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verificationcited by 28
  4. 2026ClawBench: Can AI Agents Complete Everyday Online Tasks?cited by 28
  5. 2026IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reusecited by 27
  6. 2026ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injectioncited by 25
  7. 2026GLM-OCR Technical Reportcited by 24
  8. 2026KL for a KL: On-Policy Distillation with Control Variate Baselinecited by 24
  9. 2026Qwen-AgentWorld: Language World Models for General Agentscited by 22
  10. 2026Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Whycited by 21
  11. 2026BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?cited by 20
  12. 2026Composer 2 Technical Reportcited by 20
  13. 2026Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Taskscited by 18
  14. 2026SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agentscited by 17
  15. 2026AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agentscited by 16
  16. 2026Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillationcited by 16
  17. 2026Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agentcited by 16
  18. 2026Toward Autonomous Long-Horizon Engineering for ML Researchcited by 15
  19. 2026STEPS: Selective On-Policy Self-Distillation for Reasoningcited by 15
  20. 2026SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfacescited by 15
  21. 2026When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agentscited by 15
  22. 2026Rethinking On-Policy Distillation of Large Language Models II: One Training Examplecited by 15
  23. 2026The Newton-Muon Optimizercited by 14
  24. 2026SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineeringcited by 14
  25. 2026OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoningcited by 14
  26. 2026Are Full Rollouts Necessary for On-Policy Distillation?cited by 14
  27. 2026Trajectory-Refined Distillationcited by 14
  28. 2026Demystifying On-Policy Distillation: Roles, Pathologies, and Regulationscited by 14
  29. 2026OneMillion-Bench: How Far are Language Agents from Human Experts?cited by 13
  30. 2026PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environmentscited by 13
  31. 2026Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillationcited by 13
  32. 2026Terminal-World: Scaling Terminal-Agent Environments via Agent Skillscited by 13
  33. 2026MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systemscited by 12
  34. 2026Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memorycited by 11
  35. 2026Policy and World Modeling Co-Training for Language Agentscited by 11
  36. 2026AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?cited by 11
  37. 2026HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attentioncited by 10
  38. 2026textttYC-Bench: Benchmarking AI Agents for Long-Term Planning and Consistent Executioncited by 10

50 most cited of 502 All 502 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
  2. 2025A Survey of Vibe Coding with Large Language Models
  3. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
  4. 2026Cross-Benchmark Transfer from RL on Agentic Coding Tasks
  5. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
  6. 2025Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
  7. 2025AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents
  8. 2025Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning