通过共享前缀评估算子贡献，实现多智能体推理的高效路由选择。
Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning
- 基于状态匹配的下游比较，精准分配算子信用度。
- 在6个基准上提升准确率，推理成本显著降低。
- 适合需要高效推理的复杂任务场景使用。
多智能体推理（MAR）通过迭代解法交换与优化提升推理可靠性。现有自适应MAR方法通常依赖查询级标签或轨迹级回报学习路由决策，但此类粗粒度监督无法准确估计多步协作中各算子的状态条件效用。我们提出TreeCredit，一种用于高效自适应MAR的共享前缀信用分配框架。其核心思想是通过状态匹配的下游比较来估计算子效用，而非直接将轨迹级结果归因于先前决策。TreeCredit通过从同一中间状态扩展候选算子构建共享前缀协作树，并基于终端正确性及完整延续的累积额外成本，为每个状态-算子对分配优先级信用。这些结构化信用转化为状态局部算子偏好，用于训练轻量级成对状态路由器，在推理时动态选择下一可执行算子。六项推理基准实验表明，TreeCredit在适度提升准确率的同时大幅降低推理开销，优于代表性MAR方法的精度-成本权衡。
原文摘要 · Abstract (English)
Multi-agent reasoning (MAR) improves reasoning reliability through iterative solution exchange and refinement. Existing adaptive MAR methods typically learn routing decisions from query-level labels or trajectory-level returns, but such coarse supervision cannot accurately estimate the state-conditioned utility of individual operators in multi-step collaboration. We propose TreeCredit, a shared-prefix credit assignment framework for efficient adaptive MAR. Its core insight is to estimate operator utility through state-matched downstream comparisons, rather than directly attributing trajectory-level outcomes to preceding decisions. TreeCredit constructs shared-prefix collaboration trees by expanding candidate operators from the same intermediate state and assigns each state--operator pair a correctness-prioritized suffix credit based on the terminal correctness and cumulative additional cost of its complete continuation. These structured credits are converted into state-local operator preferences to train a lightweight pairwise state router, which dynamically selects the next admissible operator during inference. Experiments on six reasoning benchmarks show that TreeCredit modestly improves accuracy while substantially reducing inference cost, achieving a better accuracy--cost trade-off than representative MAR methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。