# Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation

arXiv: https://arxiv.org/abs/2609.01603 · HTML: https://mlsanity.com/paper/2609.01603/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 38 of its 59 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 38)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [tinyBenchmarks: evaluating LLMs with fewer examples](https://mlsanity.com/paper/2402.14992/) (2024)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [Anchor Points: Benchmarking Models with Much Fewer Examples](https://mlsanity.com/paper/2309.08638/) (2023)
- [DebugBench: Evaluating Debugging Capability of Large Language Models](https://mlsanity.com/paper/2401.04621/) (2024)
- [Efficient Benchmarking of Language Models](https://mlsanity.com/paper/2308.11696/) (2023)
- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [Learning with Privileged Information for Efficient Image Super-Resolution](https://mlsanity.com/paper/2007.07524/) (2020)
- [Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory](https://mlsanity.com/paper/2505.15055/) (2025)
- [metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models](https://mlsanity.com/paper/2407.12844/) (2024)
- [Variational Item Response Theory: Fast, Accurate, and Expressive](https://mlsanity.com/paper/2002.00276/) (2020)
- [HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation](https://mlsanity.com/paper/2406.06918/) (2024)
- [RACE: Retrieval-Augmented Commit Message Generation](https://mlsanity.com/paper/2203.02700/) (2022)
- [OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution](https://mlsanity.com/paper/2505.04606/) (2025)
- [RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation](https://mlsanity.com/paper/2412.17744/) (2024)
- [What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond](https://mlsanity.com/paper/2503.20589/) (2025)
- [Do Question Answering Modeling Improvements Hold Across Benchmarks?](https://mlsanity.com/paper/2102.01065/) (2021)
- [RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories](https://mlsanity.com/paper/2601.22706/) (2026)
- [Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark](https://mlsanity.com/paper/2412.18573/) (2024)
- [The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks](https://mlsanity.com/paper/2310.17514/) (2023)
- [Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation](https://mlsanity.com/paper/2502.13576/) (2025)
- [CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents](https://mlsanity.com/paper/2406.11589/) (2024)

## Abstract (arXiv)

Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-benchmark performance, but are largely result-only: they fit historical pass/fail response matrices or static task semantics, discarding how agents solve problems. We propose PTA-IRT, a Privileged Trajectory-Aware Item Response Theory framework that fuses process and outcome signals. Historical execution trajectories supply process-level evidence beyond pass/fail, such as explored context, attempted edits, and solving paths, which PTA-IRT uses as privileged information for calibration subset selection and ability estimation. Under low calibration budgets, PTA-IRT consistently outperforms prior IRT baselines on score and ranking recovery across four SWE benchmarks. Code and data are publicly available at https://github.com/DeepSoftwareAnalytics/PTA-IRT.