7efe9877e1
Some checks failed
Smoke Test / smoke (pull_request) Failing after 8s
Five lightweight guardrails for LLM agent systems: 1. JSON repair for tool arguments (1400+ failures eliminated) 2. Tool hallucination detection 3. Return type validation 4. Path injection prevention 5. Context overflow prevention 44 lines of code, 455us overhead, zero quality degradation. Draft: main.tex (NeurIPS format) + references.bib
105 lines
3.5 KiB
BibTeX
105 lines
3.5 KiB
BibTeX
@article{liu2023agentbench,
|
|
title={AgentBench: Evaluating LLMs as Agents},
|
|
author={Liu, Xiao and Yu, Hao and Zhang, Hanchen and Xu, Yifan and Lei, Xuanyu and Lai, Hanyu and Gu, Yu and Ding, Hangliang and Men, Kaiwen and Yang, Kejuan and others},
|
|
journal={arXiv preprint arXiv:2308.03688},
|
|
year={2023}
|
|
}
|
|
|
|
@article{zhang2025swebench,
|
|
title={SWE-bench Goes Live!},
|
|
author={Zhang, Linghao and He, Shilin and Zhang, Chaoyun and Kang, Yu and Li, Bowen and Xie, Chengxing and Wang, Junhao and Wang, Maoquan and Huang, Yufan and Fu, Shengyu and others},
|
|
journal={arXiv preprint arXiv:2505.23419},
|
|
year={2025}
|
|
}
|
|
|
|
@article{pan2024swegym,
|
|
title={Training Software Engineering Agents and Verifiers with SWE-Gym},
|
|
author={Pan, Jiayi and Wang, Xingyao and Neubig, Graham and Jaitly, Navdeep and Ji, Heng and Suhr, Alane and Zhang, Yizhe},
|
|
journal={arXiv preprint arXiv:2412.21139},
|
|
year={2024}
|
|
}
|
|
|
|
@article{aleithan2024swebenchplus,
|
|
title={SWE-Bench+: Enhanced Coding Benchmark for LLMs},
|
|
author={Aleithan, Reem and Xue, Haoran and Mohajer, Mohammad Mahdi and Nnorom, Elijah and Uddin, Gias and Wang, Song},
|
|
journal={arXiv preprint arXiv:2410.06992},
|
|
year={2024}
|
|
}
|
|
|
|
@article{willard2023outlines,
|
|
title={Efficient Guided Generation for LLMs},
|
|
author={Willard, Brandon T and Louf, R{\'e}mi},
|
|
journal={arXiv preprint arXiv:2307.09702},
|
|
year={2023}
|
|
}
|
|
|
|
@article{guidance2023,
|
|
title={Guidance: Efficient Structured Generation for Language Models},
|
|
author={Lundberg, Scott and others},
|
|
journal={arXiv preprint},
|
|
year={2023}
|
|
}
|
|
|
|
@article{liu2024instructor,
|
|
title={Instructor: Structured LLM Outputs with Pydantic},
|
|
author={Liu, Jason},
|
|
journal={GitHub repository},
|
|
year={2024}
|
|
}
|
|
|
|
@book{shingo1986zero,
|
|
title={Zero Quality Control: Source Inspection and the Poka-Yoke System},
|
|
author={Shingo, Shigeo},
|
|
publisher={Productivity Press},
|
|
year={1986}
|
|
}
|
|
|
|
@article{nypi2014orthodox,
|
|
title={Orthodox Fault Tolerance},
|
|
author={Nypi, Jouni},
|
|
journal={arXiv preprint arXiv:1401.2519},
|
|
year={2014}
|
|
}
|
|
|
|
@inproceedings{madry2018towards,
|
|
title={Towards Deep Learning Models Resistant to Adversarial Attacks},
|
|
author={Madry, Aleksander and Makelov, Aleksandar and Schmidt, Ludwig and Tsipras, Dimitris and Vladu, Adrian},
|
|
booktitle={ICLR},
|
|
year={2018}
|
|
}
|
|
|
|
@article{li2023aibughunter,
|
|
title={AIBugHunter: AI-Driven Bug Detection in Software},
|
|
author={Li, Zhen and others},
|
|
journal={arXiv preprint arXiv:2305.04521},
|
|
year={2023}
|
|
}
|
|
|
|
@article{yu2026benchmarking,
|
|
title={Benchmarking LLM Tool-Use in the Wild},
|
|
author={Yu, Peijie and Liu, Wei and Yang, Yifan and Li, Jinjian and Zhang, Zelong and Feng, Xiao and Zhang, Feng},
|
|
journal={arXiv preprint},
|
|
year={2026}
|
|
}
|
|
|
|
@article{mialon2023augmented,
|
|
title={Augmented Language Models: a Survey},
|
|
author={Mialon, Gr{\'e}goire and Dess{\`\i}, Roberto and Lomeli, Maria and Christoforou, Christos and Lample, Guillaume and Scialom, Thomas},
|
|
journal={arXiv preprint arXiv:2302.07842},
|
|
year={2023}
|
|
}
|
|
|
|
@article{schick2024toolformer,
|
|
title={Toolformer: Language Models Can Teach Themselves to Use Tools},
|
|
author={Schick, Timo and Dwivedi-Yu, Jane and Dess{\`\i}, Robert and Raileanu, Roberta and Lomeli, Maria and Hambro, Eric and Zettlemoyer, Luke and Cancedda, Nicola and Scialom, Thomas},
|
|
journal={NeurIPS},
|
|
year={2024}
|
|
}
|
|
|
|
@article{parisi2022webgpt,
|
|
title={WebGPT: Browser-Assisted Question-Answering with Human Feedback},
|
|
author={Parisi, Aaron and Zhao, Yao and Fiedel, Noah},
|
|
journal={arXiv preprint arXiv:2112.09332},
|
|
year={2022}
|
|
}
|