TableMind++: 一种面向工具增强表格推理的不确定性感知程序化代理
TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning
AI总结：
TableMind++通过引入不确定性感知推理框架，有效缓解LLM的幻觉问题，提升表格推理的准确性和鲁棒性。
摘要：
表格推理需要模型同时执行语义理解和精确的数值运算。大多数现有方法依赖于对表格的单轮推理范式，这导致上下文溢出和数值敏感性弱。为了解决这些限制，我们先前提出了TableMind作为一种基于调优的自主程序化代理，它在轻量级大语言模型（LLM）中模拟人类般的交互。TableMind通过包含监督微调（SFT）在过滤后的高质量数据和通过多视角奖励以及Rank-Aware Policy Optimization（RAPO）算法的强化学习（RL）的两阶段训练策略来内部化规划、行动和反思。虽然TableMind为程序化代理建立了坚实的基础，但LLM的内在随机性仍然是一个关键挑战，导致幻觉。在本文中，我们通过引入一种新的不确定性感知推理框架来扩展这一基础，以缓解幻觉。具体而言，我们提出了记忆引导的计划修剪，以检索历史轨迹以验证并过滤掉逻辑上错误的计划以解决信念不确定性。为了确保执行精度，我们引入了基于置信度的动作细化，它监控令牌级概率以检测并自我纠正语法噪声以缓解随机不确定性。最后，我们采用双加权轨迹聚合来合成多个推理路径的稳健共识。在多样化的基准测试中，TableMind++在多个基准测试中持续优于先前的基线和专有模型，以验证将自主训练与不确定性量化相结合的有效性。我们的代码可供使用。
英文摘要：
Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow and weak numerical sensitivity. To address these limitations, we previously proposed TableMind as a tuning-based autonomous programmatic agent that simulates human-like interaction within a lightweight large language model (LLM). TableMind internalizes planning, action, and reflection through a two-stage training strategy involving supervised fine-tuning (SFT) on filtered high-quality data and reinforcement learning (RL) via a multi-perspective reward and the Rank-Aware Policy Optimization (RAPO) algorithm. While TableMind establishes a solid foundation for programmatic agents, the inherent stochasticity of LLMs remains a critical challenge that leads to hallucinations. In this paper, we extend this foundation to TableMind++ by introducing a novel uncertainty-aware inference framework to mitigate hallucinations. Specifically, we propose memory-guided plan pruning to retrieve historical trajectories for validating and filtering out logically flawed plans to address epistemic uncertainty. To ensure execution precision, we introduce confidence-based action refinement which monitors token-level probabilities to detect and self-correct syntactic noise for aleatoric uncertainty mitigation. Finally, we employ dual-weighted trajectory aggregation to synthesize a robust consensus from multiple reasoning paths. Extensive experiments on diverse benchmarks demonstrate that TableMind++ consistently outperforms previous baselines and proprietary models to validate the effectiveness of integrating autonomous training with uncertainty quantification. Our code is available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
