mlsanityData to 7 Oct 2026

Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation

arXiv 2601.21469 ↗First posted 29 Jan 2026cs.SE cs.AIcited by 0

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

also in 1 more
Abstract (arXiv)

While Large Language Models (LLMs) have catalyzed breakthroughs in automated code generation, Small Language Models (SLMs) often encounter reasoning bottlenecks and failure loops when addressing complex logical requirements. To overcome these challenges, we propose DebateCoder, a multi-agent collaborative framework designed to improve the reasoning ability of SLMs (e.g., Pangu-1B) in resource-constrained environments. DebateCoder uses a structured role-playing protocol with three agents: User Agent (A_UA), Technical Agent (A_TA), and Quality Assurance Agent (A_QA). It also includes an Adaptive Confidence Gating mechanism with a 95% threshold to balance accuracy and inference efficiency. In addition, we introduce a multi-turn deliberation module and a reviewer-guided analytical debugging loop for orthogonal pre-generation debate and post-generation refinement. Experiments on HumanEval and MBPP show that DebateCoder achieves 70.12% Pass@1 on HumanEval, outperforming MapCoder while reducing API overhead by about 35%. These results indicate that collaborative protocols can mitigate limitations of small-parameter models and provide a scalable, efficient approach to high-quality automated software engineering.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 29 of its 32 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

29 of 32 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solving18 May
  2. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  10. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  11. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  12. 2023StarCoder: may the source be with you!cited by 790
15 more
  1. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  2. 2024A Survey on Large Language Models for Code Generationcited by 646
  3. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  4. 2024AutoCodeRover: Autonomous Program Improvementcited by 272
  5. 2023Self-collaboration Code Generation via ChatGPTcited by 255
  6. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 191
  7. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  8. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110
  9. 2023CodeScore: Evaluating Code Generation by Learning Code Executioncited by 66
  10. 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Codecited by 61
  11. 2025Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognitioncited by 61
  12. 2025Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applicationscited by 26
  13. 2025Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Fastercited by 15
  14. 2025A Survey on Collaborative Mechanisms Between Large and Small Language Modelscited by 12
  15. 2025Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latencycited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
  2. 2026Demystifying Multi-Agent Debate: The Role of Confidence and Diversity
  3. 2025Enhancing Multi-Agent Debate System Performance via Confidence Expression
  4. 2025Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks
  5. 2025MARS: toward more efficient multi-agent collaboration for LLM reasoning
  6. 2026ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning
  7. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  8. 2026Confidence Composition for Multiagent Language Model Systems