# AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

arXiv: https://arxiv.org/abs/2603.14465 · HTML: https://mlsanity.com/paper/2603.14465/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 30 of 31)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [VinePPO: Refining Credit Assignment in RL Training of LLMs](https://mlsanity.com/paper/2410.01679/) (2024)
- [AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories](https://mlsanity.com/paper/2504.08942/) (2025)
- [Neural Machine Translation: A Review and Survey](https://mlsanity.com/paper/1912.02047/) (2019)
- [Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models](https://mlsanity.com/paper/2403.12881/) (2024)
- [PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models](https://mlsanity.com/paper/2501.03124/) (2025)
- [AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories](https://mlsanity.com/paper/2410.07706/) (2024)
- [Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning](https://mlsanity.com/paper/2504.15275/) (2025)
- [Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist](https://mlsanity.com/paper/2407.08733/) (2024)
- [Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents](https://mlsanity.com/paper/2506.21252/) (2025)
- [AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents](https://mlsanity.com/paper/2602.06485/) (2026)

## Built on by (most cited first, 30 of 31)

- [SOD: Step-wise On-policy Distillation for Small Language Model Agents](https://mlsanity.com/paper/2605.07725/) (2026)
- [SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution](https://mlsanity.com/paper/2605.18401/) (2026)
- [SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use](https://mlsanity.com/paper/2607.01874/) (2026)
- [Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories](https://mlsanity.com/paper/2606.02060/) (2026)
- [SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior](https://mlsanity.com/paper/2606.11543/) (2026)
- [Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks](https://mlsanity.com/paper/2608.03222/) (2026)
- [WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking](https://mlsanity.com/paper/2603.27343/) (2026)
- [OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories](https://mlsanity.com/paper/2605.29253/) (2026)
- [Interactive Evaluation Requires a Design Science](https://mlsanity.com/paper/2605.17829/) (2026)
- [Sandboxed Coding Agents are Competitive Omni-modal Task Solvers](https://mlsanity.com/paper/2606.00579/) (2026)
- [The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation](https://mlsanity.com/paper/2607.24720/) (2026)
- [LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering](https://mlsanity.com/paper/2608.28281/) (2026)
- [trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories](https://mlsanity.com/paper/2609.00038/) (2026)
- [ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents](https://mlsanity.com/paper/2607.28037/) (2026)
- [Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation](https://mlsanity.com/paper/2608.00794/) (2026)
- [More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight](https://mlsanity.com/paper/2608.23941/) (2026)
- [Grounded Checklist Partial Credit for Agent Skill Trajectories](https://mlsanity.com/paper/2608.27487/) (2026)
- [Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision](https://mlsanity.com/paper/2609.02057/) (2026)
- [Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes](https://mlsanity.com/paper/2609.34262/) (2026)
- [Inducing Process Supervision from Outcome-Only Reinforcement Learning](https://mlsanity.com/paper/2609.36641/) (2026)
- [Agent Step Value: Auditing Evaluation-Channel Sensitivity in Black-Box Agent Traces](https://mlsanity.com/paper/2607.04419/) (2026)
- [Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?](https://mlsanity.com/paper/2607.26041/) (2026)
- [MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning](https://mlsanity.com/paper/2608.03882/) (2026)
- [Testing and Evaluation of Agentic AI Systems In Military Command and Control](https://mlsanity.com/paper/2608.20597/) (2026)
- [SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs](https://mlsanity.com/paper/2609.10901/) (2026)
- [AgentPProf: Semantic Profiler for Long Horizon AI Agents](https://mlsanity.com/paper/2609.20301/) (2026)
- [DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement](https://mlsanity.com/paper/2609.21423/) (2026)
- [TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces](https://mlsanity.com/paper/2609.33295/) (2026)
- [AgentSWE: Can Coding Agents Build the Agent You Actually Want?](https://mlsanity.com/paper/2610.13361/) (2026)
- [ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence](https://mlsanity.com/paper/2610.14381/) (2026)

## Abstract (arXiv)

While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce irreversible side effects, making accurate step-level verification critical. However, existing process-level benchmarks are predominantly confined to closed-world mathematical domains, failing to capture the dynamic and open-ended nature of tool execution. To bridge this gap, we introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories. The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement. It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity. Extensive experiments reveal key insights: (1) weaker policy models exhibit inflated ratios of correct steps due to early termination; (2) distinguishing neutral and erroneous actions remains a significant challenge for current models; and (3) process-derived signals provide complementary value to outcome supervision, significantly enhancing test-time scaling. We hope AgentProcessBench can foster future research in reward models and pave the way toward general agents. The code and data are available at https://github.com/RUCBM/AgentProcessBench.