mlsanityData to 14 Oct 2026

The Conductor and the Engine: A Path Towards Co-Designed Reasoning

arXiv 2509.19762 ↗First posted 24 Sep 2025cs.AIcited by 0

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

also in 1 more
Abstract (arXiv)

Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as model verbosity and poor instruction following lead to wasted compute. We analyze this capability-cost trade-off and introduce an optimized reasoning workflow (cepo) that empowers smaller open-source models to outperform models multiple times their size. We will open-source this workflow to enable further research. Our work demonstrates a clear path toward co-designing orchestration frameworks with the underlying model capabilities to unlock powerful reasoning in small-to-medium sized models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 20 of its 35 references that are in the map. First posted on arXiv 24 Sep 2025.

Builds on

20 of 35 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024OpenAI o1 System Card21 Dec
  2. 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code12 Mar

Other references · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  6. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  7. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  8. 2025s1: Simple test-time scalingcited by 1,341
  9. 2025Group Sequence Policy Optimizationcited by 835
  10. 2025LIMO: Less is More for Reasoningcited by 498
  11. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 464
  12. 2024SciCode: A Research Coding Benchmark Curated by Scientistscited by 178
5 more
  1. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solverscited by 138
  2. 2024Rho-1: Not All Tokens Are What You Needcited by 133
  3. 2025Concise Reasoning via Reinforcement Learningcited by 79
  4. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  5. 2025Read Quietly, Think Aloud: Decoupling Comprehension and Reasoning in LLMscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  2. 2026A Comprehensive Evaluation of LLM Reasoning: From Single-Model to Multi-Agent Paradigms
  3. 2025Exploring the Necessity of Reasoning in LLM-based Agent Scenarios
  4. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
  5. 2026When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty
  6. 2026Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
  7. 2026Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
  8. 2026PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces