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

arXiv: https://arxiv.org/abs/2602.07773 · HTML: https://mlsanity.com/paper/2602.07773/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 34 of its 53 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 34)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025)
- [ZeroSearch: Incentivize the Search Capability of LLMs without Searching](https://mlsanity.com/paper/2505.04588/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations](https://mlsanity.com/paper/2506.13651/) (2025)
- [WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents](https://mlsanity.com/paper/2509.06501/) (2025)
- [MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling](https://mlsanity.com/paper/2511.11793/) (2025)
- [Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL](https://mlsanity.com/paper/2508.13167/) (2025)
- [AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress](https://mlsanity.com/paper/2511.08325/) (2025)
- [SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models](https://mlsanity.com/paper/2506.01062/) (2025)
- [Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning](https://mlsanity.com/paper/2505.14069/) (2025)
- [Tongyi DeepResearch Technical Report](https://mlsanity.com/paper/2510.24701/) (2025)
- [DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL](https://mlsanity.com/paper/2509.10446/) (2025)
- [Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution](https://mlsanity.com/paper/2509.25301/) (2025)
- [Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward](https://mlsanity.com/paper/2508.12800/) (2025)
- [O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering](https://mlsanity.com/paper/2505.16582/) (2025)
- [DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning](https://mlsanity.com/paper/2505.24332/) (2025)
- [Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge](https://mlsanity.com/paper/2502.12501/) (2025)
- [Open Data Synthesis For Deep Research](https://mlsanity.com/paper/2509.00375/) (2025)
- [InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.15872/) (2025)

## Built on by (most cited first, 5 of 5)

- [Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?](https://mlsanity.com/paper/2605.19196/) (2026)
- [Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation](https://mlsanity.com/paper/2604.10741/) (2026)
- [AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs](https://mlsanity.com/paper/2608.26004/) (2026)
- [InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization](https://mlsanity.com/paper/2609.06438/) (2026)
- [Agent-Editing World Model: Rethinking World Modeling for LLM Agents](https://mlsanity.com/paper/2609.28416/) (2026)

## Abstract (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.