arXiv cs.CL· Manh Nguyen, Sunil Gupta, Hung Le·· 12 小时前AI 评分38
多思考还是多阅读？共享上下文下推理的 token 预算理论
Think More or Read More? A Token-Budget Theory of Reasoning with Shared Context
AI 导读
研究提出 token 预算理论，刻画共享 token 窗口下“读上下文”与“推理生成”的取舍：读得越多，可用于思考的预算越少。该理论基于允许相关误差的 Condorcet 陪审团模型，对多智能体辩论给出最优智能体数量的闭式预测，且可由单智能体测量估计，无需实际运行辩论。
正文 · 原文
Abstract:Reasoning systems increasingly improve answers by incorporating additional context into the model's input, from multi-agent debate, where agents read their peers' responses, to self-refinement, where a model revisits its own drafts. In these systems, communication consumes context as one agent's output becomes another's input. We study the regime where token reading and generation draw on one fixed token window, so every token spent reading is a token that cannot be spent reasoning. We develop a \textbf{token-budget theory} that formalizes this trade-off, modeling accuracy as a function of the reasoning budget remaining after reading and aggregating votes with a Condorcet jury model that permits correlated errors. For multi-agent debate, the theory gives a closed-form prediction for the optimal number of agents. This quantity is estimated from single-agent measurements, allowing the optimal group size to be determined without running debate, and the same accounting extends to a heterogeneous set of different models. We empirically verify our theory and show that, at the predicted group size, our method outperforms strong baselines under the tightest calibration spend, where debate-calibrated rules can afford only one or two questions. Self-refinement obeys the same accounting, with its own draft in place of a peer message. The theory further predicts that communication pays only when the gain in the accuracy ceiling exceeds the reasoning room spent on reading, with this condition tightening as the window shrinks. Across five open models and four reasoning tasks, self-consistency matches or beats deployed debate at $93$\% of $980$ matched window-and-group-size settings, with the gap being largest under tight windows and nearly disappearing at a loose one, consistent with the theory. Under a shared window, how much room a model has left to \textit{think matters more than what it reads}.
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.23246 [cs.CL] |
| (or arXiv:2610.23246v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23246 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Manh Nguyen [view email]
[v1]
Fri, 16 Oct 2026 10:18:15 UTC (332 KB)
来源：arXiv cs.CL · arxiv.org