TabTracer: Monte Carlo Tree Search for Complex Table Reasoning with Large Language Models

2026-02-15

AI Summary

This work proposes TabTracer, a novel framework addressing key limitations of large language models in tabular reasoning—namely error propagation, weak backtracking capability, redundant reasoning trajectories, and excessive token consumption. TabTracer enables efficient and verifiable reasoning by explicitly tracking intermediate table states and integrating execution feedback through Monte Carlo Tree Search (MCTS). The framework introduces several innovations: a state snapshot rollback mechanism, UCB1-based action selection, and a monotonicity-gated deduplication strategy. It further incorporates typed operation validation, lightweight numerical checks, state hashing, and budget-aware pruning to enhance reliability and efficiency. Evaluated on TabFact, WikiTQ, and CRT benchmarks, TabTracer achieves up to a 6.7% absolute improvement in accuracy while reducing token usage by 59%–84% compared to existing approaches.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Reasoning under Uncertainty: Uncertainty Representations
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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%.

Problem

• table reasoning
• error propagation
• backtracking
• token cost
• redundancy

Innovation

• Monte Carlo Tree Search
• table reasoning
• step-level verification
• state tracking
• token efficiency