paper-with-me

홈 › Papers

SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents

2026-02-08 · Chen Zhang, Kuicai Dong, Dexun Li, Wenjun Li, Qu Yang, Wei Han, Yong Liu arxiv

Recent deep search agents built on large reasoning models (LRMs) excel at complex question answering by iteratively planning, acting, and gathering evidence, a capability known as search-integrated reasoning. However, mainstream approaches often train this ability using only outcome-based supervision, neglecting the quality of intermediate thoughts and actions. We introduce SRR-Judge, a framework for reliable step-level assessment of reasoning and search actions. Integrated into a modified ReAct-style rate-and-refine workflow, SRR-Judge provides fine-grained guidance for search-integrated reasoning and enables efficient post-training annotation. Using SRR-annotated data, we apply an iterative rejection sampling fine-tuning procedure to enhance the deep search capability of the base agent. Empirically, SRR-Judge delivers more reliable step-level evaluations than much larger models such as DeepSeek-V3.1, with its ratings showing strong correlation with final answer correctness. Moreover, aligning the policy with SRR-Judge annotated trajectories leads to substantial performance gains, yielding over a 10 percent average absolute pass@1 improvement across challenging deep search benchmarks.

📄 PDF Abstract BibTeX arXiv:2602.07773

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Scaling Unverifiable Rewards: A Case Study on Visual Insights

2025-12-27 · Shuyu Gan, James Mooney, Pan Hao, Renxiang Wang 외 arxiv

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline wh…

Story Generation

Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning

2025-08-03 · Derin Cayir, Renjie Tao, Rashi Rungta, Kai Sun 외 arxiv

Large Language Models (LLMs) have demonstrated remarkable progress through preference-based fine-tuning, which critically depends on the quality of the underlying training data. While human feedback is essential for impr…

Rethinking Code Refinement: Learning to Judge Code Efficiency

2024-10-29 · Minju Seo, Jinheon Baek, Sung Ju Hwang

Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. Howev…

Language ModelingLanguage Modelling

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning

2025-04-18 · Jianing Wang, Jin Jiang, Yang Liu, Mengdi Zhang 외

In this paper, we introduce a new \emph{process prejudge} strategy in LLM reasoning to demonstrate that bootstrapping with process prejudge allows the LLM to adaptively anticipate the errors encountered when advancing th…

Reinforcement Learning (RL)

LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation

2025-06-12 · Ngoc Phuoc An Vo, Brent Paulovicks, Vadim Sheinin

In an effort to automatically evaluate and select the best model and improve code quality for automatic incident remediation in IT Automation, it is crucial to verify if the generated code for remediation action is synta…

Code Generation