TabTracer:基于大语言模型的复杂表格推理的蒙特卡洛树搜索
TabTracer: Monte Carlo Tree Search for Complex Table Reasoning with Large Language Models
AI总结:
TabTracer通过多步工具调用和显式状态跟踪,提升复杂表格推理的准确率并降低token成本。
摘要:
大型语言模型(LLMs)已发展为自然语言表格推理的强大工具,其中主要有两种方法。基于提示的方法依赖于仅语言推断或一次生成程序,没有逐步验证。基于代理的方法使用闭环工具,但验证通常是局部的,回溯有限,允许错误传播并增加成本。此外,它们依赖于链式或束式轨迹,通常具有组合冗余性,导致高token成本。在本文中,我们提出了TabTracer,一种代理框架,通过中间表格状态协调多步工具调用,具有显式的状态跟踪以进行验证和回滚。首先,它通过类型操作和轻量级数值和格式检查进行逐步验证,以提供可靠的奖励并抑制幻觉。其次,执行反馈的蒙特卡洛树搜索维护候选表格状态的搜索树,并使用反向传播的反射分数来指导UCB1选择和回滚通过版本化快照。第三,它通过预算感知剪枝、去重和状态哈希与单调性门来减少冗余,以降低token成本。在TabFact、WikiTQ和CRT数据集上的全面评估显示,TabTracer在准确率上比最先进的基线高出高达6.7%,同时将token消耗减少59-84%。
英文摘要:
Large language models (LLMs) have emerged as powerful tools for natural language table reasoning, where there are two main categories of methods. Prompt-based approaches rely on language-only inference or one-pass program generation without step-level verification. Agent-based approaches use tools in a closed loop, but verification is often local and backtracking is limited, allowing errors to propagate and increasing cost. Moreover, they rely on chain- or beam-style trajectories that are typically combinatorially redundant, leading to high token costs. In this paper, we propose TabTracer, an agentic framework that coordinates multi-step tool calls over intermediate table states, with explicit state tracking for verification and rollback. First, it enforces step-level verification with typed operations and lightweight numeric and format checks to provide reliable rewards and suppress hallucinations. Second, execution-feedback Monte Carlo Tree Search maintains a search tree of candidate table states and uses backpropagated reflection scores to guide UCB1 selection and rollback via versioned snapshots. Third, it reduces redundancy with budget-aware pruning, deduplication, and state hashing with a monotonicity gate to cut token cost. Comprehensive evaluation on TabFact, WikiTQ, and CRT datasets shows that TabTracer outperforms state-of-the-art baselines by up to 6.7% in accuracy while reducing token consumption by 59--84%.
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。