Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation

arXiv:2609.01603 · cs.SE, cs.AI, cs.CL · Submitted 2026-09-01 · Read on arXiv

cs.SE, cs.AI, cs.CL

Submitted: 2026-09-01

Updated: 2026-09-01

Code: https://github.com/DeepSoftwareAnalytics/PTA-IRT

Terminology

• Benchmark — 57× in this paper · explained in 2 episodes
• Calibration — 38× in this paper · explained in 7 episodes
• Benchmarking — 12× in this paper · explained in 3 episodes
• Item Response Theory — 10× in this paper
• Ablation — 4× in this paper · explained in 1 episode
• Clustering — 4× in this paper · explained in 2 episodes
• Distillation — 4× in this paper · explained in 2 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fisher Information — 2× in this paper · explained in 3 episodes
• Item Characteristic Curve — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• ACM International Conference on Automated Software Engineering — 1× in this paper
• Conference on Computational Natural Language Learning — 1× in this paper
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Maximum Likelihood Estimation — 1× in this paper
• Mean Absolute Error — 1× in this paper
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Variational Inference — 1× in this paper

Sources

• Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark
• What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties