{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/77011e69\"></iframe>","width":"100%","height":180,"duration":1245,"description":"\n            🤗 Upvotes: 29 | cs.CL, cs.AI\n\n            Authors:\n            Minki Kang, Jongwon Jeong, Jaewoong Cho\n\n            Title:\n            T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models\n\n            Arxiv:\n            http://arxiv.org/abs/2504.04718v1\n\n            Abstract:\n            Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined test-time compute scaling with an additional larger model as a verifier, leaving self-verification by sLMs underexplored. In this work, we investigate whether sLMs can reliably self-verify their outputs under test-time scaling. We find that even with knowledge distillation from larger verifiers, sLMs struggle with verification tasks requiring memorization, such as numerical calculations and fact-checking. To address this limitation, we propose Tool-integrated self-verification (T1), which delegates memorization-heavy verification steps to external tools, such as a code interpreter. Our theoretical analysis shows that tool integration reduces memorization demands and improves test-time scaling performance. Experiments on the MATH benchmark demonstrate that, with T1, a Llama-3.2 1B model under test-time scaling outperforms the significantly larger Llama-3.1 8B model. Moreover, T1 generalizes effectively to both mathematical (MATH500) and multi-domain knowledge-intensive tasks (MMLU-Pro). Our findings highlight the potential of tool integration to substantially improve the self-verification abilities of sLMs.\n            ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}