Research

Paper

AI LLM March 12, 2026

Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs

Authors

Kunfeng Chen, Qihuang Zhong, Juhua Liu, Bo Du, Dacheng Tao

Abstract

Tool-calling empowers Large Language Models (LLMs) to interact with external environments. However, current methods often struggle to handle massive and noisy candidate tools in long-context tool-calling tasks, limiting their real-world application. To this end, we propose Tool-DC, a Divide-and-Conquer framework for boosting tool-calling performance of LLMs. The core of Tool-DC is to reduce the reasoning difficulty and make full use of self-reflection ability of LLMs via a "Try-Check-Retry" paradigm. Specifically, Tool-DC involves two variants: 1) the training-free Tool-DC (TF), which is plug-and-play and flexible; 2) the training-based Tool-DC (TB), which is more inference-efficient. Extensive experiments show that both Tool-DC methods outperform their counterparts by a clear margin. Tool-DC (TF) brings up to +25.10% average gains against the baseline on BFCL and ACEBench benchmarks, while Tool-DC (TB) enables Qwen2.5-7B to achieve comparable or even better performance than proprietary LLMs, e.g., OpenAI o3 and Claude-Haiku-4.5.

Metadata

arXiv ID: 2603.11495
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-12
Fetched: 2026-03-14 05:03

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11495v1</id>\n    <title>Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs</title>\n    <updated>2026-03-12T03:30:01Z</updated>\n    <link href='https://arxiv.org/abs/2603.11495v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11495v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Tool-calling empowers Large Language Models (LLMs) to interact with external environments. However, current methods often struggle to handle massive and noisy candidate tools in long-context tool-calling tasks, limiting their real-world application. To this end, we propose Tool-DC, a Divide-and-Conquer framework for boosting tool-calling performance of LLMs. The core of Tool-DC is to reduce the reasoning difficulty and make full use of self-reflection ability of LLMs via a \"Try-Check-Retry\" paradigm. Specifically, Tool-DC involves two variants: 1) the training-free Tool-DC (TF), which is plug-and-play and flexible; 2) the training-based Tool-DC (TB), which is more inference-efficient. Extensive experiments show that both Tool-DC methods outperform their counterparts by a clear margin. Tool-DC (TF) brings up to +25.10% average gains against the baseline on BFCL and ACEBench benchmarks, while Tool-DC (TB) enables Qwen2.5-7B to achieve comparable or even better performance than proprietary LLMs, e.g., OpenAI o3 and Claude-Haiku-4.5.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-12T03:30:01Z</published>\n    <arxiv:comment>17 pages, 8 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Kunfeng Chen</name>\n    </author>\n    <author>\n      <name>Qihuang Zhong</name>\n    </author>\n    <author>\n      <name>Juhua Liu</name>\n    </author>\n    <author>\n      <name>Bo Du</name>\n    </author>\n    <author>\n      <name>Dacheng Tao</name>\n    </author>\n  </entry>"
}