Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917006543945728 |
|---|---|
| author | Lan, Junwei Chen, Jianlyu Liu, Zheng Li, Chaofan Bao, Siqi Lian, Defu |
| author_facet | Lan, Junwei Chen, Jianlyu Liu, Zheng Li, Chaofan Bao, Siqi Lian, Defu |
| contents | With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem requires fine-grained reasoning to accurately assess the relevance between the task and each candidate document. This capability, however, poses a significant challenge for existing IR techniques. Despite recent progress in reasoning-enhanced IR, existing approaches still face significant challenges in applicability, scalability, and efficiency. In this work, we propose Retro*, a novel approach for reasoning-intensive document retrieval. Our method introduces a rubric-based relevance scoring mechanism, enabling the model to reason about the relationship between a task and a document based on explicitly defined criteria, whereby producing a fine-grained, interpretable relevance score. Retro* also supports test-time scaling by combining multiple reasoning trajectories via score integration, which produces more reliable relevance estimates. To optimize Retro*'s reasoning capabilities, we introduce a novel reinforcement learning algorithm tailored for its relevance scoring mechanism, which employs two composite rewards to fully exploit the trajectories of each training sample. Our experiments show that Retro* outperforms existing document retrieval methods with notable advantages, leading to state-of-the-art performance on the BRIGHT benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24869 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval Lan, Junwei Chen, Jianlyu Liu, Zheng Li, Chaofan Bao, Siqi Lian, Defu Information Retrieval Artificial Intelligence Computation and Language With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem requires fine-grained reasoning to accurately assess the relevance between the task and each candidate document. This capability, however, poses a significant challenge for existing IR techniques. Despite recent progress in reasoning-enhanced IR, existing approaches still face significant challenges in applicability, scalability, and efficiency. In this work, we propose Retro*, a novel approach for reasoning-intensive document retrieval. Our method introduces a rubric-based relevance scoring mechanism, enabling the model to reason about the relationship between a task and a document based on explicitly defined criteria, whereby producing a fine-grained, interpretable relevance score. Retro* also supports test-time scaling by combining multiple reasoning trajectories via score integration, which produces more reliable relevance estimates. To optimize Retro*'s reasoning capabilities, we introduce a novel reinforcement learning algorithm tailored for its relevance scoring mechanism, which employs two composite rewards to fully exploit the trajectories of each training sample. Our experiments show that Retro* outperforms existing document retrieval methods with notable advantages, leading to state-of-the-art performance on the BRIGHT benchmark. |
| title | Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2509.24869 |