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

• URL: http://arxiv.org/abs/2603.14465v1
• Date: Sun, 15 Mar 2026 16:13:58 GMT
• Title: AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
• Abstract summary: We introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories.<n>The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement.<n>It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity.
• Score: 50.481033105867205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents [8.640998417745086]
  We introduce Trace2Tower, a transition-aware EigenTrace framework that distills raw trajectories into a robust skill hierarchy.<n>Through a novel contrastive spectral decomposition, it isolates stable, success-aligned behavioral modes while rigorously suppressing failure-prone shortcuts.<n>On ALFWorld, Trace2Tower achieves 87.31% success requiring only 10.35 steps and 0.26 invalid actions; on WebShop, it reaches 50.67% exact success.
  arXiv  Detail & Related papers  (2026-09-04T15:22:39Z)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems [47.66236392009794]
  Large Language Model(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks.<n>We propose textitTrajectory Graph Copilot, a novel framework that acts as a copilot'' for LLM agents by diagnosing potential action errors before they are executed.
  arXiv  Detail & Related papers  (2026-07-29T20:14:43Z)
• Beyond the Black Box: Interpretability of Agentic AI Tool Use [0.0]
  We introduce a mechanistic-interpretability toolkit built on Sparse Autoencoders and linear probes.<n>The framework reads model states before each action and infers both whether a tool is needed and how consequential the next tool action is likely to be.<n>We train the probes on multi-step trajectories from the NVIDIA Nemotron function-calling dataset and apply the same workflow to GPT-OSS 20B and Gemma 3 27B models.
  arXiv  Detail & Related papers  (2026-05-07T19:47:30Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Step-level Optimization for Efficient Computer-use Agents [51.29573359027217]
  We argue that strong computer-use agents remain expensive and slow in practice.<n>We propose an event-driven, step-level cascade for computer-use agents.
  arXiv  Detail & Related papers  (2026-04-29T19:59:36Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning [4.928838343487574]
  Existing uncertainty proxies focus on single-shot text generation.<n>We introduce TRACER, a trajectory-level uncertainty metric for dual-control Tool-Agent-User interaction.
  arXiv  Detail & Related papers  (2026-02-11T22:23:56Z)
• AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering [8.201374511929538]
  AgentDevel is a release engineering pipeline that iteratively runs the current agent.<n>It produces implementation-blind, symptom-level quality signals from execution traces.<n>It aggregates dominant symptom patterns and produces auditable engineering specifications.
  arXiv  Detail & Related papers  (2026-01-08T05:49:01Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems [20.846301581161978]
  Failure attribution in multi-agent systems is a critical yet unsolved challenge.<n>Current methods treat this as a pattern recognition task over long conversation logs.<n>A2P Scaffolding transforms failure attribution from pattern recognition into a structured causal inference task.
  arXiv  Detail & Related papers  (2025-09-12T16:51:15Z)
• Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference [8.823529310904162]
  Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is hampered by the challenge of failure attribution.<n>We introduce the first failure attribution framework for MAS grounded in multi-granularity causal inference.
  arXiv  Detail & Related papers  (2025-09-10T15:22:00Z)
• How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench [58.114899897566964]
  In a multi-turn conversational environment, large language models (LLMs) often struggle with consistent reasoning and adherence to domain-specific policies.<n>We propose the Input-Reformulation Multi-Agent (IRMA) framework, which automatically reformulates user queries augmented with relevant domain rules.<n>IRMA significantly outperforms ReAct, Function Calling, and Self-Reflection by 16.1%, 12.7%, and 19.1%, respectively.
  arXiv  Detail & Related papers  (2025-08-28T15:57:33Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.