mlsanityData to 14 Oct 2026

Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models

arXiv 2606.03624 ↗First posted 2 Jun 2026cs.AI cs.CLcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously. We formalize this challenge as the Constraint Adherence Problem (CAP). This paper introduces a novel framework that addresses CAP by representing instructions as a structured knowledge graph of constraints. Our approach, Constraint Relationship Graph Completion (CRGC), explicitly models relationships between constraints, identifies adherence challenges, and discovers ``bridge constraints'' that help the model better focus on and reconcile requirements. Bridge constraints act as auxiliary instructions that make primary constraints more salient and compatible. Unlike existing approaches that enhance instruction following through general training methods, CRGC specifically improves constraint satisfaction by leveraging the model's own knowledge to create better pathways for generation. Experiments across three popular instruction following datasets demonstrate that our approach reduces constraint violations by 39% compared to standard prompting while maintaining reasoning abilities of large reasoning models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 41 of its 49 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

41 of 49 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering23 May
  2. 2024How often are errors in natural language reasoning due to paraphrastic variability?17 Apr
  3. 2023Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning1 Jun
  4. 2023Fact-Checking Complex Claims with Program-Guided Reasoning22 May

Other references · 37

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2024Qwen2.5 Technical Reportcited by 4,942
  8. 2024GPT-4o System Cardcited by 4,588
  9. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  11. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  12. 2024Mixtral of Expertscited by 1,823
25 more
  1. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  2. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  3. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  4. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  5. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 378
  6. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 225
  7. 2022Instruction Induction: From Few Examples to Natural Language Task Descriptionscited by 152
  8. 2024Benchmarking Complex Instruction-Following with Multiple Constraints Compositioncited by 152
  9. 2024InFoBench: Evaluating Instruction Following Ability in Large Language Modelscited by 135
  10. 2023FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Modelscited by 117
  11. 2024Distilling an End-to-End Voice Assistant Without Instruction Training Datacited by 39
  12. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraintscited by 35
  13. 2023Prompt Optimization via Adversarial In-Context Learningcited by 33
  14. 2024LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarioscited by 33
  15. 2025MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusioncited by 30
  16. 2024Answer is All You Need: Instruction-following Text Embedding via Answering the Questioncited by 27
  17. 2024RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructionscited by 25
  18. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  19. 2024OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Followingcited by 14
  20. 2024Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?cited by 8
  21. 2024AutoDSL: Automated domain-specific language design for structural representation of procedures with constraintscited by 6
  22. 2023STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generationcited by 5
  23. 2024STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Modelscited by 5
  24. 2022Learning Action Conditions from Instructional Manuals for Instruction Understandingcited by 4
  25. 2025MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
  2. 2026ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
  3. 2025Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
  4. 2025Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models
  5. 2026Compliance vs. Sensibility: On the Reasoning Controllability in Large Language Models
  6. 2026Constraint-First Reasoning: A Training-Free Protocol for Exploiting Answer-Space Constraints in Mathematical Problem Solving
  7. 2025When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs
  8. 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models