FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search

arXiv:2606.00660 · cs.CL · Submitted 2026-05-30 · Read on arXiv

cs.CL

Submitted: 2026-05-30

Updated: 2026-09-01

Code: https://github.com/XuZhao0/fineverify

Terminology

• Verification — 89× in this paper · explained in 2 episodes
• Accuracy — 48× in this paper · explained in 1 episode
• Agentic Search — 46× in this paper · explained in 1 episode
• Benchmark — 44× in this paper · explained in 2 episodes
• Verifier — 18× in this paper · explained in 2 episodes
• Aggregation — 17× in this paper · explained in 1 episode
• Adam — 15× in this paper · explained in 2 episodes
• Test-time Scaling — 15× in this paper · explained in 2 episodes
• Trace — 10× in this paper · explained in 2 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• LLM-as-a-Judge — 3× in this paper · explained in 3 episodes
• Score Function — 3× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes

Sources

• BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
• Training Verifiers to Solve Math Word Problems
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection
• DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
• xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
• Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline
• Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
• WebGPT: Browser-assisted question-answering with human feedback
• ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking
• Learning to Reason Across Parallel Samples for LLM Reasoning
• WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
• DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
• OpenAI GPT-5 System Card
• Scaling Long-Horizon LLM Agent via Context-Folding
• Tongyi DeepResearch Technical Report
• Evaluating Stochasticity in Deep Research Agents
• Recursive Language Models
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
• A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering