arXiv subjects

Qunhong Zeng

Publications and source records attributed to Qunhong Zeng.

4 recordsLinked to original sources

arXiv2026

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

cs.AI↗

arXiv2026

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding

Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are heterogeneous and persist across interactions. To fill this gap, we introduce OctoBench, which benchmarks scaffold-aware instruction following in repository-grounded agentic coding. OctoBench includes 34 environments and 217 tasks instantiated under three scaffold types, and is paired with 7,098 objective checklist items. To disentangle solving the task from following the rules, we provide an automated observation-and-scoring toolkit that captures full trajectories and performs fine-grained checks. Experiments on eight representative models reveal a systematic gap between task-solving and scaffold-aware compliance, underscoring the need for training and evaluation that explicitly targets heterogeneous instruction following. We release the benchmark to support reproducible benchmarking and to accelerate the development of more scaffold-aware coding agents.

cs.CL↗

arXiv2025

Tool-integrated Reinforcement Learning for Repo Deep Search

Issue localization, the process of identifying code locations that need modification to resolve software issues, is a critical yet challenging task in software development. The semantic gap between natural language issue descriptions and faulty code requires complex multi-hop reasoning through code dependencies. Existing LLM-based agents attempt to address this by integrating repository retrieval tools. However, this transforms issue localization into a demanding task we call Repo Deep Search, which requires the LLM to effectively utilize various repository retrieval tools throughout a multi-step reasoning and navigation process. To tackle this challenge, we present ToolTrain, a two-stage tool-integrated training framework combining rejection-sampled supervised fine-tuning and tool-integrated reinforcement learning to enhance LLMs' ability to use retrieval tools for issue localization. Experimental results show that ToolTrain-trained models achieve state-of-the-art performance, with our 32B model even surpassing Claude-3.7 on function-level localization. The results also show that improved localization performance translates to better end-to-end issue resolution performance. This further demonstrates that training for issue localization is a viable and effective strategy for improving automated software development.

cs.SE↗

arXiv2025

Evaluating Generated Commit Messages with Large Language Models

Commit messages are essential in software development as they serve to document and explain code changes. Yet, their quality often falls short in practice, with studies showing significant proportions of empty or inadequate messages. While automated commit message generation has advanced significantly, particularly with Large Language Models (LLMs), the evaluation of generated messages remains challenging. Traditional reference-based automatic metrics like BLEU, ROUGE-L, and METEOR have notable limitations in assessing commit message quality, as they assume a one-to-one mapping between code changes and commit messages, leading researchers to rely on resource-intensive human evaluation. This study investigates the potential of LLMs as automated evaluators for commit message quality. Through systematic experimentation with various prompt strategies and state-of-the-art LLMs, we demonstrate that LLMs combining Chain-of-Thought reasoning with few-shot demonstrations achieve near human-level evaluation proficiency. Our LLM-based evaluator significantly outperforms traditional metrics while maintaining acceptable reproducibility, robustness, and fairness levels despite some inherent variability. This work conducts a comprehensive preliminary study on using LLMs for commit message evaluation, offering a scalable alternative to human assessment while maintaining high-quality evaluation.

cs.SE↗