mlsanityData to 7 Oct 2026

InCoder-32B-Thinking: Industrial Code World Model for Thinking

arXiv 2604.03144 ↗First posted 3 Apr 2026cs.AR cs.AI cs.CLcited by 4

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reasoning traces showing how engineers reason about hardware constraints and timing semantics. In this work, we propose InCoder-32B-Thinking, trained on the data from the Error-driven Chain-of-Thought (ECoT) synthesis framework with an industrial code world model (ICWM) to generate reasoning traces. Specifically, ECoT generates reasoning chains by synthesizing the thinking content from multi-turn dialogue with environmental error feedback, explicitly modeling the error-correction process. ICWM is trained on domain-specific execution traces from Verilog simulation, GPU profiling, etc., learns the causal dynamics of how code affects hardware behavior, and enables self-verification by predicting execution outcomes before actual compilation. All synthesized reasoning traces are validated through domain toolchains, creating training data matching the natural reasoning depth distribution of industrial tasks. Evaluation on 14 general (81.3% on LiveCodeBench v5) and 9 industrial benchmarks (84.0% in CAD-Coder and 38.0% on KernelBench) shows InCoder-32B-Thinking achieves top-tier open-source results across all domains.GPU Optimization

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 56 of its 71 references that are in the map. First posted on arXiv 3 Apr 2026.

Builds on

56 of 71 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation30 May
  2. 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset27 May
  3. 2025VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation17 May
  4. 2025OpenCodeReasoning: Advancing Data Distillation for Competitive Coding2 Apr
  5. 2024RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning2 Oct
  6. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code12 Mar
  7. 2023Structured Chain-of-Thought Prompting for Code Generation11 May

Other references · 49

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2021Program Synthesis with Large Language Modelscited by 3,509
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  8. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  9. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  10. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  11. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
  12. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
37 more
  1. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
  2. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 527
  3. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 502
  4. 2026Kimi K2.5: Visual Agentic Intelligencecited by 449
  5. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 325
  6. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 294
  7. 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 246
  8. 2024From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Stepcited by 225
  9. 2025KernelBench: Can LLMs Write Efficient GPU Kernels?cited by 206
  10. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 197
  11. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 162
  12. 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Serverscited by 89
  13. 2025CWM: An Open-Weights LLM for Research on Code Generation with World Modelscited by 87
  14. 2024o1-Coder: an o1 Replication for Codingcited by 77
  15. 2025Kevin: Multi-Turn RL for Generating CUDA Kernelscited by 73
  16. 2025TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operatorscited by 68
  17. 2024FullStack Bench: Evaluating LLMs as Full Stack Coderscited by 56
  18. 2025CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Rewardcited by 53
  19. 2023Large Language Models for Compiler Optimizationcited by 52
  20. 2025Seed-Coder: Let the Code Model Curate Data for Itselfcited by 46
  21. 2026CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generationcited by 41
  22. 2024LeDex: Training LLMs to Better Self-Debug and Explain Codecited by 39
  23. 2025Kimi-Dev: Agentless Training as Skill Prior for SWE-Agentscited by 35
  24. 2024Mercury: A Code Efficiency Benchmark for Code Large Language Modelscited by 34
  25. 2024Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agentscited by 25
  26. 2023Exploring and Characterizing Large Language Models For Embedded System Development and Debuggingcited by 20
  27. 2025VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verificationcited by 15
  28. 2025RealBench: Benchmarking Verilog Generation Models with Real-World IP Designscited by 14
  29. 2025VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correctioncited by 12
  30. 2026AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Unitscited by 11
  31. 2025ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Modelscited by 10
  32. 2025KAT-Coder Technical Reportcited by 7
  33. 2024EmbedGenius: Towards Automated Software Development for Generic Embedded IoT Systemscited by 6
  34. 2025ArchXBench: A Complex Digital Systems Benchmark Suite for LLM Driven RTL Synthesiscited by 6
  35. 2025SuperCoder: Assembly Program Superoptimization with Large Language Modelscited by 5
  36. 2025EmbedAgent: Benchmarking Large Language Models in Embedded System Developmentcited by 5
  37. 2026InCoder-32B: Code Foundation Model for Industrial Scenarioscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compressioncited by 12
  2. 2026SPPO: Sequence-Level PPO for Long-Horizon Reasoning Taskscited by 7
  3. 2026GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Modelscited by 0
  4. 2026CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
  2. 2025ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development
  3. 2025ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications
  4. 2024MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs
  5. 2025Towards LLM-based Root Cause Analysis of Hardware Design Failures
  6. 2026How LLMs Fail and Generalize in RTL Coding for Hardware Design?
  7. 2025QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
  8. 2025Generating Verifiable Chain of Thoughts from Exection-Traces