OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering
This addresses the problem of scalable and accurate table QA for users needing to query diverse tables, though it is incremental as it builds on existing tool-augmented and RL fine-tuning methods.
The paper tackles open-domain table question answering by proposing an end-to-end agentic framework that integrates tool calls (search API and SQL executor) into a large language model, achieving an accuracy improvement from single-digit zero-shot performance to over 0.86 exact match on a held-out test set.
Open-domain table question answering traditionally relies on a two-stage pipeline: static table retrieval followed by a closed-domain answer. In contrast, we propose an end-to-end agentic framework that embeds multi-turn tool calls-using a BM25+-based search API and a SQLite SQL executor-directly into a large language model. To further adapt a compact 4B-parameter model, we introduce a two-stage fine-tuning process: supervised cold-start on easy questions, then Async GRPO reinforcement learning on harder cases with LoRA adapters and a rollout buffer. This unified approach enables the model to jointly retrieve, reason, and execute queries, yielding a dramatic accuracy improvement from single-digit zero-shot performance to over 0.86 exact match on a held-out test set. Our results underscore the effectiveness of integrating structured tool calls with targeted RL fine-tuning for scalable, accurate table QA. The code is available at https://github.com/TabibitoQZP/OpenTableR1.