mlsanityData to 7 Oct 2026

Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution

arXiv 2604.16322 ↗First posted 27 Feb 2026cs.SE cs.AI cs.PLcited by 1

On the map: Synthetic data and self-improvement for LLMs → Code and instruction data synthesis

Abstract (arXiv)

Interpreting and following human instructions is a critical capability of large language models (LLMs) in automatic programming. However, synthesizing large-scale instruction-paired coding data remains largely unexplored and is particularly challenging when ensuring logical compatibility among multiple constraints. In this study, we propose IFCodeEvolve, an actor-schema co-evolution framework for instruction following coding data generation. By representing instructions as parametric function schema, we construct a library that covers the vast instruction space via dynamic constraint instantiation. Building upon this, Monte Carlo Tree Search (MCTS) sampler is applied to efficiently navigate this space, utilizing actor model feedback as a dynamic termination signal. Furthermore, to progressively explore challenging problems, we introduce a co-evolving paradigm that iteratively advances both the actor model and the schema library, via schema composition and mutation, based on sampler statistics. Empirical results demonstrate that IFCodeEvolve significantly boosts base model performance, with our 32B model achieving parity with proprietary SOTA models. Additionally, we contribute IFCodeBench, a comprehensive human-verified benchmark equipped with solutions and robust AST-based verification.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Code and instruction data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 33 of its 40 references that are in the map. First posted on arXiv 27 Feb 2026.

Builds on

33 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models19 Jun
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructions20 Dec

Other references · 31

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2021Program Synthesis with Large Language Modelscited by 3,509
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  10. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  11. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  12. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
19 more
  1. 2023Large Language Models as Optimizerscited by 830
  2. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  3. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  4. 2024Automated Design of Agentic Systemscited by 360
  5. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 323
  6. 2024DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Datacited by 225
  7. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
  8. 2025Generalizing Verifiable Instruction Followingcited by 178
  9. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 171
  10. 2023ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generationcited by 166
  11. 2025Multi-SWE-bench: A Multilingual Benchmark for Issue Resolvingcited by 165
  12. 2023FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Modelscited by 112
  13. 2025BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Provingcited by 82
  14. 2025LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMscited by 67
  15. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agentscited by 66
  16. 2025Seed-Coder: Let the Code Model Curate Data for Itselfcited by 46
  17. 2025CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generationcited by 18
  18. 2025Accelerating Scientific Discovery with Autonomous Goal-evolving Agentscited by 16
  19. 2025IFEvalCode: Controlled Code Generationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Followingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding
  2. 2025PACIFIC: a framework for generating benchmarks to check Precise Automatically Checked Instruction Following In Code
  3. 2024Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search
  4. 2026OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
  5. 2024Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
  6. 2024SelfCodeAlign: Self-Alignment for Code Generation
  7. 2024Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models
  8. 2025SWE-IF: Aligning Code Evaluation with Human Preference