Score: 1

Reducing Cognitive Load in Multi-Agent Reinforcement Learning for Mathematical Problem Solving: Decoupling Reasoning and Code Generation

Published: August 12, 2025 | arXiv ID: 2508.08882v1

By: Dayu Wang , Jiaye Yang , Weikang Li and more

BigTech Affiliations: Baidu

Potential Business Impact:

Splits math problems between two AI helpers.

Current tool-integrated mathematical reasoning systems often adopt a single-agent paradigm, where one large language model handles problem reasoning, code generation, and code execution in an integrated workflow. While this design eases coordination, we hypothesize that it imposes cognitive load interference, as the agent must interleave long-horizon reasoning with precise program synthesis. We validate this hypothesis through a controlled comparison between a reasoning-only agent and a reasoning-plus-code agent, finding that the latter produces significantly fewer correct reasoning paths despite having tool-calling capabilities. To address this, we propose a dual-agent hybrid framework: a Reasoning Agent performs stepwise problem decomposition, and a Code Agent handles code generation and execution. Training combines imitation learning and reinforcement learning: the Code Agent receives strong rewards for matching intermediate ground-truth programs and weaker rewards for valid execution, while the Reasoning Agent is optimized chiefly via final-answer accuracy using advantage estimation to credit intermediate steps. This decoupled role design reduces cognitive interference and promotes stable reasoning-coding coordination.

Country of Origin
🇨🇳 China

Page Count
9 pages

Category
Computer Science:
Artificial Intelligence