AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios

• URL: http://arxiv.org/abs/2505.16944v1
• Date: Thu, 22 May 2025 17:31:10 GMT
• Title: AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
• Authors: Yunjia Qi, Hao Peng, Xiaozhi Wang, Amy Xin, Youfeng Liu, Bin Xu, Lei Hou, Juanzi Li,
• Abstract summary: Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications.<n>AgentIF is the first benchmark for systematically evaluating LLM instruction following ability in agentic scenarios.
• Score: 51.46347732659174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications. Growing research efforts aim to develop LLM-based agents to address practical demands, introducing a new challenge: agentic scenarios often involve lengthy instructions with complex constraints, such as extended system prompts and detailed tool specifications. While adherence to such instructions is crucial for agentic applications, whether LLMs can reliably follow them remains underexplored. In this paper, we introduce AgentIF, the first benchmark for systematically evaluating LLM instruction following ability in agentic scenarios. AgentIF features three key characteristics: (1) Realistic, constructed from 50 real-world agentic applications. (2) Long, averaging 1,723 words with a maximum of 15,630 words. (3) Complex, averaging 11.9 constraints per instruction, covering diverse constraint types, such as tool specifications and condition constraints. To construct AgentIF, we collect 707 human-annotated instructions across 50 agentic tasks from industrial application agents and open-source agentic systems. For each instruction, we annotate the associated constraints and corresponding evaluation metrics, including code-based evaluation, LLM-based evaluation, and hybrid code-LLM evaluation. We use AgentIF to systematically evaluate existing advanced LLMs. We observe that current models generally perform poorly, especially in handling complex constraint structures and tool specifications. We further conduct error analysis and analytical experiments on instruction length and meta constraints, providing some findings about the failure modes of existing LLMs. We have released the code and data to facilitate future research.

Related papers

• On LLM-Assisted Generation of Smart Contracts from Business Processes [0.08192907805418582]
  Large language models (LLMs) have changed the reality of how software is produced.<n>We present an exploratory study to investigate the use of LLMs for generating smart contract code from business process descriptions.<n>Our results show that LLM performance falls short of the perfect reliability required for smart contract development.
  arXiv  Detail & Related papers  (2025-07-30T20:39:45Z)
• Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications [0.0]
  LLMs can be used to solve complex tasks by combining reasoning techniques, code generation, and software execution across multiple, potentially specialized LLMs.<n>This paper introduces an agent schema language and the execution and evaluation of the specifications through a multi-agent system architecture and prototype.<n>Test cases involving cybersecurity tasks indicate the feasibility of the architecture and evaluation approach.
  arXiv  Detail & Related papers  (2025-06-12T08:16:17Z)
• EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models [65.48902212293903]
  We present the Extremely Complex Instruction Following Benchmark (EIFBENCH) for evaluating large language models (LLMs)<n>EIFBENCH includes multi-task scenarios that enable comprehensive assessment across diverse task types concurrently.<n>We also propose the Segment Policy Optimization (SegPO) algorithm to enhance the LLM's ability to accurately fulfill multi-task workflow.
  arXiv  Detail & Related papers  (2025-06-10T02:39:55Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation [1.7268889851975326]
  We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks.<n>Unlike traditional approaches relying on natural language prompts, our benchmark emphasizes the ability of LLMs to interpret and implement functionality directly from test cases.
  arXiv  Detail & Related papers  (2025-05-13T23:47:12Z)
• BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions [72.56339136017759]
  We introduce BigCodeBench, a benchmark that challenges Large Language Models (LLMs) to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks.<n>Our evaluation shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%.<n>We propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information.
  arXiv  Detail & Related papers  (2024-06-22T15:52:04Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model [15.558269067931374]
  We propose STEVE-2, a hierarchical knowledge distillation framework for open-ended embodied tasks. After distillation, embodied agents can complete complex, open-ended tasks without additional expert guidance.
  arXiv  Detail & Related papers  (2024-04-06T12:51:00Z)
• 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)
• Agent Lumos: Unified and Modular Training for Open-Source Language Agents [89.78556964988852]
  We introduce LUMOS, one of the first frameworks for training open-source LLM-based agents. LUMOS features a learnable, unified, and modular architecture with a planning module that learns high-level subgoal generation. We collect large-scale, unified, and high-quality training annotations derived from diverse ground-truth reasoning rationales.
  arXiv  Detail & Related papers  (2023-11-09T00:30:13Z)
• Formally Specifying the High-Level Behavior of LLM-Based Agents [24.645319505305316]
  LLMs have emerged as promising tools for solving challenging problems without the need for task-specific finetuned models. Currently, the design and implementation of such agents is ad hoc, as the wide variety of tasks that LLM-based agents may be applied to naturally means there can be no one-size-fits-all approach to agent design. We propose a minimalistic generation framework that simplifies the process of building agents.
  arXiv  Detail & Related papers  (2023-10-12T17:24:15Z)
• Can Large Language Models Understand Real-World Complex Instructions? [54.86632921036983]
  Large language models (LLMs) can understand human instructions, but struggle with complex instructions. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions. We propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
  arXiv  Detail & Related papers  (2023-09-17T04:18:39Z)

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.