# Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification

arXiv: https://arxiv.org/abs/2601.15808 · HTML: https://mlsanity.com/paper/2601.15808/

## Key facts

- Cited by 22 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 38 of its 58 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 30 of 38)

- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025)
- [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [Autonomous Evaluation and Refinement of Digital Agents](https://mlsanity.com/paper/2404.06474/) (2024)
- [OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation](https://mlsanity.com/paper/2505.23885/) (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)
- [Reinforcement Learning with Rubric Anchors](https://mlsanity.com/paper/2508.12790/) (2025)
- [AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories](https://mlsanity.com/paper/2504.08942/) (2025)
- [Tongyi DeepResearch Technical Report](https://mlsanity.com/paper/2510.24701/) (2025)
- [Scaling Test-time Compute for LLM Agents](https://mlsanity.com/paper/2506.12928/) (2025)
- [WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model](https://mlsanity.com/paper/2504.21024/) (2025)
- [Self-Challenging Language Model Agents](https://mlsanity.com/paper/2506.01716/) (2025)
- [OneThinker: All-in-one Reasoning Model for Image and Video](https://mlsanity.com/paper/2512.03043/) (2025)
- [AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents](https://mlsanity.com/paper/2502.05957/) (2025)
- [Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training](https://mlsanity.com/paper/2508.00414/) (2025)
- [Guided Self-Evolving LLMs with Minimal Human Supervision](https://mlsanity.com/paper/2512.02472/) (2025)
- [OAgents: An Empirical Study of Building Effective Agents](https://mlsanity.com/paper/2506.15741/) (2025)
- [WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback](https://mlsanity.com/paper/2505.20013/) (2025)
- [WebSuite: Systematically Evaluating Why Web Agents Fail](https://mlsanity.com/paper/2406.01623/) (2024)
- [PROGRESSLM: Towards Progress Reasoning in Vision-Language Models](https://mlsanity.com/paper/2601.15224/) (2026)
- [TapeAgents: a Holistic Framework for Agent Development and Optimization](https://mlsanity.com/paper/2412.08445/) (2024)

## Built on by (most cited first, 22 of 22)

- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)
- [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026)
- [Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design](https://mlsanity.com/paper/2603.28376/) (2026)
- [Verified Critical Step Optimization for LLM Agents](https://mlsanity.com/paper/2602.03412/) (2026)
- [When Is Enough Not Enough? Illusory Completion in Search Agents](https://mlsanity.com/paper/2602.07549/) (2026)
- [AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge](https://mlsanity.com/paper/2603.07019/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration](https://mlsanity.com/paper/2604.18131/) (2026)
- [SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning](https://mlsanity.com/paper/2605.01489/) (2026)
- [Agentic Context Learning with Self-Discovered Specification](https://mlsanity.com/paper/2607.09794/) (2026)
- [SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution](https://mlsanity.com/paper/2608.05573/) (2026)
- [Grounded Checklist Partial Credit for Agent Skill Trajectories](https://mlsanity.com/paper/2608.27487/) (2026)
- [Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering](https://mlsanity.com/paper/2602.22508/) (2026)
- [Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher](https://mlsanity.com/paper/2606.13710/) (2026)
- [Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents](https://mlsanity.com/paper/2608.31076/) (2026)
- [Self-Designed Evaluators and Warm Memory for Long-Horizon Agents](https://mlsanity.com/paper/2609.33717/) (2026)
- [Traverse: Learning When to Remember, Reset, and Redirect for Long-Horizon Web Search](https://mlsanity.com/paper/2609.37082/) (2026)
- [VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks](https://mlsanity.com/paper/2610.00972/) (2026)
- [Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization](https://mlsanity.com/paper/2610.01017/) (2026)
- [PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces](https://mlsanity.com/paper/2610.15208/) (2026)
- [Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks](https://mlsanity.com/paper/2610.17609/) (2026)
- [Beyond the Verdict: Agentic Code Judging with Verifiable Feedback](https://mlsanity.com/paper/2610.18760/) (2026)

## Abstract (arXiv)

Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving. While the majority of existing efforts focus on enhancing policy capabilities via post-training, we propose an alternative paradigm: self-evolving the agent's ability by iteratively verifying the policy model's outputs, guided by meticulously crafted rubrics. This approach gives rise to the inference-time scaling of verification, wherein an agent self-improves by evaluating its generated answers to produce iterative feedback and refinements. We derive the rubrics based on an automatically constructed DRA Failure Taxonomy, which systematically classifies agent failures into five major categories and thirteen sub-categories. We present DeepVerifier, a rubrics-based outcome reward verifier that leverages the asymmetry of verification and outperforms vanilla agent-as-judge and LLM judge baselines by 12%-48% in meta-evaluation F1 score. To enable practical self-evolution, DeepVerifier integrates as a plug-and-play module during test-time inference. The verifier produces detailed rubric-based feedback, which is fed back to the agent for iterative bootstrapping, refining responses without additional training. This test-time scaling delivers 8%-11% accuracy gains on challenging subsets of GAIA and XBench-DeepSearch when powered by capable closed-source LLMs. Finally, to support open-source advancement, we release DeepVerifier-4K, a curated supervised fine-tuning dataset of 4,646 high-quality agent steps focused on DRA verification. These examples emphasize reflection and self-critique, enabling open models to develop robust verification capabilities.