Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents
- URL: http://arxiv.org/abs/2412.18371v2
- Date: Wed, 25 Dec 2024 09:32:18 GMT
- Title: Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents
- Authors: Kaiwen Ning, Jiachi Chen, Jingwen Zhang, Wei Li, Zexu Wang, Yuming Feng, Weizhe Zhang, Zibin Zheng,
- Abstract summary: We present the first study focused on identifying and detecting defects in LLM Agents.
We collected and analyzed 6,854 relevant posts from StackOverflow to define 8 types of agent defects.
Our results show that Agentable achieved an overall accuracy of 88.79% and a recall rate of 91.03%.
- Score: 31.126001253902416
- License:
- Abstract: AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources and tools through prompts. In such agents, the workflow integrates developer-written code, which manages framework construction and logic control, with LLM-generated natural language that enhances dynamic decision-making and interaction. However, discrepancies between developer-implemented logic and the dynamically generated content of LLMs in terms of behavior and expected outcomes can lead to defects, such as tool invocation failures and task execution errors. These issues introduce specific risks, leading to various defects in LLM-based AI Agents, such as service interruptions. Despite the importance of these issues, there is a lack of systematic work that focuses on analyzing LLM-based AI Agents to uncover defects in their code. In this paper, we present the first study focused on identifying and detecting defects in LLM Agents. We collected and analyzed 6,854 relevant posts from StackOverflow to define 8 types of agent defects. For each type, we provided detailed descriptions with an example. Then, we designed a static analysis tool, named Agentable, to detect the defects. Agentable leverages Code Property Graphs and LLMs to analyze Agent workflows by efficiently identifying specific code patterns and analyzing natural language descriptions. To evaluate Agentable, we constructed two datasets: AgentSet, consists of 84 real-world Agents, and AgentTest, which contains 78 Agents specifically designed to include various types of defects. Our results show that Agentable achieved an overall accuracy of 88.79% and a recall rate of 91.03%. Furthermore, our analysis reveals the 889 defects of the AgentSet, highlighting the prevalence of these defects.
Related papers
- Interactive Agents to Overcome Ambiguity in Software Engineering [61.40183840499932]
AI agents are increasingly being deployed to automate tasks, often based on ambiguous and underspecified user instructions.
Making unwarranted assumptions and failing to ask clarifying questions can lead to suboptimal outcomes.
We study the ability of LLM agents to handle ambiguous instructions in interactive code generation settings by evaluating proprietary and open-weight models on their performance.
arXiv Detail & Related papers (2025-02-18T17:12:26Z) - AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions [10.686849324750556]
Automated gEneral buG reproductIon Scripts generation framework, named AEGIS, is the first agent-based framework for the task.
AEGIS can improve the relative resolved rate of Agentless by 12.5%.
arXiv Detail & Related papers (2024-11-27T03:16:47Z) - An Empirical Study on LLM-based Agents for Automated Bug Fixing [2.433168823911037]
Large language models (LLMs) and LLM-based Agents have been applied to fix bugs automatically.
We examine seven proprietary and open-source systems on the SWE-bench Lite benchmark for automated bug fixing.
arXiv Detail & Related papers (2024-11-15T14:19:15Z) - REDO: Execution-Free Runtime Error Detection for COding Agents [3.9903610503301072]
Execution-free Error Detection for COding Agents (REDO) is a method that integrates runtime errors with static analysis tools.
We demonstrate that REDO outperforms current state-of-the-art methods by achieving a 11.0% higher accuracy and a 9.1% higher weighted F1 score.
arXiv Detail & Related papers (2024-10-10T18:06:29Z) - Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [117.94654815220404]
G"odel Agent is a self-evolving framework inspired by the G"odel machine.
G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
arXiv Detail & Related papers (2024-10-06T10:49:40Z) - Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
Large language models (LLMs) have transformed the development of embodied intelligence.
This paper uncovers a significant backdoor security threat within this process.
By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
arXiv Detail & Related papers (2024-08-06T01:20:12Z) - WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [85.95607119635102]
Large language models (LLMs) can mimic human-like intelligence.
WorkArena++ is designed to evaluate the planning, problem-solving, logical/arithmetic reasoning, retrieval, and contextual understanding abilities of web agents.
arXiv Detail & Related papers (2024-07-07T07:15:49Z) - Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning [56.82041895921434]
Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities.
When used as agents for dealing with complex problems in the real world, their performance is far inferior to large commercial models such as ChatGPT and GPT-4.
arXiv Detail & Related papers (2024-03-29T03:48:12Z) - AgentFL: Scaling LLM-based Fault Localization to Project-Level Context [11.147750199280813]
This paper presents AgentFL, a multi-agent system based on ChatGPT for automated fault localization.
By simulating the behavior of a human developer, AgentFL models the FL task as a three-step process, which involves comprehension, navigation, and confirmation.
The evaluation on the widely used Defects4J-V1.2.0 benchmark shows that AgentFL can localize 157 out of 395 bugs within Top-1.
arXiv Detail & Related papers (2024-03-25T01:58:19Z) - Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models [31.509994889286183]
We introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of language models (LMs) in reasoning, acting, and planning.
A key feature of our approach is the incorporation of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism.
LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT
arXiv Detail & Related papers (2023-10-06T17:55:11Z) - AgentBench: Evaluating LLMs as Agents [88.45506148281379]
Large Language Models (LLMs) are becoming increasingly smart and autonomous, targeting real-world pragmatic missions beyond traditional NLP tasks.
We present AgentBench, a benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
arXiv Detail & Related papers (2023-08-07T16:08:11Z)
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.