ScholarPulse 日报 2026-10-22

2026-10-22 学术简报：2 篇。论文提出评估大模型端到端量化投研能力的基准 Quant-Arena，实测表明前沿模型在真实 A 股 2024 年样本外测试中均未战胜等权基准。

今日速览

序号	标题	来源	日期	主题	推荐等级
1	Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research	arXiv	2026-10-21	AI-Agent	高
2	Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization	arXiv	2026-10-21	AI-Agent	高

重点论文与技术动态

1. Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research

来源：arXiv
日期：2026-10-21
作者/机构：Houde Qian, Zheng Jiang, Wenyi Li, Chenxi Xu, Xinjie Lin, Yuzhao Peng
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.CL, cs.AI, cs.CE

一句话结论

论文提出评估大模型端到端量化投研能力的基准 Quant-Arena，实测表明前沿模型在真实 A 股 2024 年样本外测试中均未战胜等权基准。

核心内容

构建了覆盖“构建特征与代码-获取历史反馈-冻结策略测试”的端到端量化研发闭环评测体系与榜单。
评分以实现超额收益为主，兼顾信号质量与特征多样性，并计入交易限制及订单簿模拟的冲击成本。
评测了 9 个前沿模型，GPT-6 Astra 得分最高，但在 2024 年测试中无一模型跑赢等权市场。

方法与数据

采用中国 A 股真实市场数据，以 2022–2023 年作为策略研发与反馈期，2024 年作为封存的样本外评测期。
运行现金账户评估器模拟交易，基于模拟订单簿估算市场冲击成本并施加交易约束。

价值判断

值得关注：打破了单点代码评测局限，首次系统验证大模型量化全流程闭环及样本外泛化能力。
可复用点：整合现金账户、模拟订单簿冲击与多维指标的量化评估框架及公开提交机制。
局限/待核查：所有模型在 2024 年均未击败等权市场，模型全流程自主生成实战策略的有效性仍待验证。

摘要

Quantitative research is an iterative loop: a researcher proposes a market hypothesis, implements it as an executable signal, tests it on historical data, and decides what to keep. Existing benchmarks score formulas, code, or individual trading decisions, leaving open whether large language models (LLMs) can complete this loop and produce strategies that work beyond the research period. We introduce Quant-Arena, a benchmark and public leaderboard for end-to-end quantitative research on real A-share market data. A model constructs features and stock-scoring code, receives feedback only on 2022--2023, and freezes one strategy for assessment on the sealed year 2024. A cash-account evaluator applies trading constraints and costs, including market impact estimated from a simulated order book. Scores are dominated by realized excess return and complemented by signal quality and the diversity of features used by the strategy. We evaluate nine frontier models, among which GPT-6 Astra scores highest; yet no model beats the equal-weight market in 2024. Quant-Arena is open to submissions from any model or agent harness.

2. Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization

来源：arXiv
日期：2026-10-21
作者/机构：Hanmin Li, Yury Demidovich, Peter Richtárik
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.MA, cs.AI, math.OC

一句话结论

本文将并行AI智能体协作建模为图结构离散块优化，通过分数着色合并局部修改，有效解决合并冲突并提供理论收益与几何收敛保证。

核心内容

依赖图中的独立集确保编辑兼容性，最优分数着色合并可保证保留紧致的 $1/\chi_f(G)$ 局部改进（ $\chi_f(G)$ 为分数色数）。
在条件局部改进与误差界条件下协作实现几何收敛，支持通过线性规划权衡智能体分配的时间与计算成本。
实验中有效化解了代码修复合并冲突，并在路网分割中保留了优化收益，在路线规划中缩减了15%的中位耗时。

方法与数据

采用已知依赖图的离散块优化与分数着色理论；在代码修复、3个公开路网（90次配对运行）及路径搜索（12次配对运行）上评估。

价值判断

值得关注：首次将多智能体并发合并与图的分数色数严格绑定，给出了收益保留下界与几何收敛性证明。
可复用点：基于分数着色的协调合并机制，以及权衡时间与成本的智能体分配线性规划模型。
局限/待核查：依赖已知依赖图与可精确评估的目标函数；并行换取耗时缩减伴随更高的Token成本，且部分任务路径成本存在波动。

摘要

Parallel AI agents can produce useful local edits yet degrade a shared solution when their edits are combined. We model this coordination problem as discrete block optimization with an exactly evaluable objective and a known dependency graph. Independent sets certify compatible edits whose verified gains, measured against the same current solution, add exactly. A coordinator constructs a safe compatible candidate and can also evaluate interacting edits to capture favorable interactions. We prove that an optimal fractional coloring yields a merger that preserves a $1/χ_f(G)$ fraction of the total verified local improvement, where $χ_f(G)$ is the graph's fractional chromatic number. This guarantee is tight among mergers that select a subset of the same proposals. Under conditional local-improvement guarantees and a block error-bound condition, repeated collaboration converges geometrically in the objective gap. The rate separates task structure, agent allocation, and computation cost, yielding a linear program for agent assignment and an explicit time-cost trade-off. Code-repair experiments show that verified merging resolves conflicts between individually useful edits that cause naive merging to fail. On larger conflict-free tasks, parallel agents reduce modeled completion time at higher input-token-equivalent cost. On three public road networks, fractional integration retains 922 units of verified graph-cut improvement across 90 paired runs. For route-search agents sharing exclusive access to vehicle routes, fractional scheduling reduces measured wall time by a median of 15% across twelve paired runs, with route-cost changes varying across runs.