mlsanityData to 14 Oct 2026

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

arXiv 2508.06471 ↗First posted 8 Aug 2025cs.CLcited by 467

On the map: LLM reasoning → Reasoning benchmarks and evaluation

also in 2 more
Abstract (arXiv)

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.

Key facts. Cited by 467 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 42 of its 50 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

42 of 50 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Qwen3 Technical Report14 May
  2. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks19 Dec
  3. 2024Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries19 Sep
  4. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb

Other references · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  6. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  9. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  10. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  11. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  12. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
26 more
  1. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  2. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  3. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  4. 2016Bag of Tricks for Efficient Text Classificationcited by 876
  5. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  6. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 723
  7. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  8. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 559
  9. 2025Humanity's Last Examcited by 491
  10. 2025Muon is Scalable for LLM Trainingcited by 428
  11. 2024Measuring short-form factuality in large language modelscited by 373
  12. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
  13. 2023SemDeDup: Data-efficient learning at web-scale through semantic deduplicationcited by 303
  14. 2020Query-Key Normalization for Transformerscited by 280
  15. 2025MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attentioncited by 263
  16. 2022Efficient Training of Language Models to Fill in the Middlecited by 255
  17. 2024Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Expertscited by 205
  18. 2023SafetyBench: Evaluating the Safety of Large Language Modelscited by 199
  19. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 180
  20. 2024SciCode: A Research Coding Benchmark Curated by Scientistscited by 178
  21. 2024Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Datasetcited by 160
  22. 2025FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Languagecited by 143
  23. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  24. 2025QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learningcited by 50
  25. 2024Fewer Truncations Improve Language Modelingcited by 35
  26. 2025Seed-X: Building Strong Multilingual Translation LLM with 7B Parameterscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 129; 2026: 338.

467 papers.

Sort:

By area:

  1. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  2. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 215
  3. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  4. 2026Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMscited by 137
  5. 2025MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Serverscited by 109
  6. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 103
  7. 2025Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluationcited by 92
  8. 2025MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scalingcited by 81
  9. 2026Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agentscited by 79
  10. 2026ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedbackcited by 72
  11. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agentscited by 68
  12. 2025Tongyi DeepResearch Technical Reportcited by 66
38 more
  1. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 61
  2. 2025Baichuan-M2: Scaling Medical Capability with Large Verifier Systemcited by 59
  3. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 59
  4. 2026Endless Terminals: Scaling RL Environments for Terminal Agentscited by 54
  5. 2025VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applicationscited by 53
  6. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  7. 2026REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agentscited by 49
  8. 2025Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Modelscited by 48
  9. 2026DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraintscited by 46
  10. 2025StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?cited by 44
  11. 2025REAP the Experts: Why Pruning Prevails for One-Shot MoE compressioncited by 44
  12. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  13. 2026Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 42
  14. 2025Scaling Agents via Continual Pre-trainingcited by 40
  15. 2025Agentic Entropy-Balanced Policy Optimizationcited by 40
  16. 2025Toward Training Superintelligent Software Agents through Self-Play SWE-RLcited by 40
  17. 2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Datacited by 39
  18. 2026LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routingcited by 38
  19. 2026Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 38
  20. 2026Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learningcited by 37
  21. 2025MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Modelscited by 34
  22. 2025MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool usecited by 32
  23. 2026ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Trainingcited by 32
  24. 2025ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agentscited by 31
  25. 2025BugPilot: Complex Bug Generation for Efficient Learning of SWE Skillscited by 30
  26. 2025CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Criticcited by 30
  27. 2025ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Datasetcited by 30
  28. 2025Single-stream Policy Optimizationcited by 28
  29. 2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 27
  30. 2025Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearchcited by 27
  31. 2025UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarioscited by 26
  32. 2025Streaming Video Instruction Tuningcited by 26
  33. 2026FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimizationcited by 25
  34. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  35. 2026AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Conditioncited by 23
  36. 2025Introducing LongCat-Flash-Thinking: A Technical Reportcited by 22
  37. 2025Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Mathcited by 22
  38. 2026SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Trainingcited by 22

50 most cited of 467 All 467 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
  2. 2026GLM-5: from Vibe Coding to Agentic Engineering
  3. 2025Reasoning Language Models: A Blueprint
  4. 2026Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model
  5. 2026GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
  6. 2026Mach-Mind-4-Flash Technical Report
  7. 2026LongCat-Flash-Thinking-2601 Technical Report
  8. 2023GLoRE: Evaluating Logical Reasoning of Large Language Models