iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model
cs.AI, cs.CL, cs.SE
Submitted: 2026-08-28
Updated: 2026-08-28
Code: https://github.com/bingreeky/iCoder
Terminology
Sources
- Self-Improving LLM Agents at Test-Time
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- RTLScout: Joint Agentic Code and Synthesis Optimization for Efficient Digital Circuits
- CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
- Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs
- Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap
- MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
- Synthesis-in-the-Loop Evaluation of LLMs for RTL Generation: Quality, Reliability, and Failure Modes
- AQuA: Recursively Self-Improving Quantitative Trading Research Agents
- RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
- Reinforcement Learning via Self-Distillation
- AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search
- RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs
- Recursive Harness Self-Improvement
- SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
- TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
- Large Language Model Based Agent for Automated Discovery in Computational Physics
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection