# Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

arXiv: https://arxiv.org/abs/2508.13143 · HTML: https://mlsanity.com/paper/2508.13143/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 28 of 28)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification](https://mlsanity.com/paper/2308.07921/) (2023)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration](https://mlsanity.com/paper/2408.15978/) (2024)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [TaskWeaver: A Code-First Agent Framework](https://mlsanity.com/paper/2311.17541/) (2023)
- [MarsCode Agent: AI-native Automated Bug Fixing](https://mlsanity.com/paper/2409.00899/) (2024)
- [SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories](https://mlsanity.com/paper/2409.07440/) (2024)
- [CYCLE: Learning to Self-Refine the Code Generation](https://mlsanity.com/paper/2403.18746/) (2024)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [MARE: Multi-Agents Collaboration Framework for Requirements Engineering](https://mlsanity.com/paper/2405.03256/) (2024)
- [PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback](https://mlsanity.com/paper/2412.03578/) (2024)
- [Requirements are All You Need: From Requirements to Code with LLMs](https://mlsanity.com/paper/2406.10101/) (2024)
- [Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment](https://mlsanity.com/paper/2501.14296/) (2025)
- [CIBench: Evaluating Your LLMs with a Code Interpreter Plugin](https://mlsanity.com/paper/2407.10499/) (2024)

## Built on by (most cited first, 20 of 20)

- [ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection](https://mlsanity.com/paper/2605.03378/) (2026)
- [Inference-Time Budget Control for LLM Search Agents](https://mlsanity.com/paper/2605.05701/) (2026)
- [Failure as a Process: An Anatomy of CLI Coding Agent Trajectories](https://mlsanity.com/paper/2607.09510/) (2026)
- [Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering](https://mlsanity.com/paper/2601.14470/) (2026)
- [Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes](https://mlsanity.com/paper/2603.06847/) (2026)
- [Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents](https://mlsanity.com/paper/2603.12634/) (2026)
- [TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems](https://mlsanity.com/paper/2605.26563/) (2026)
- [Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows](https://mlsanity.com/paper/2509.23735/) (2025)
- [From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents](https://mlsanity.com/paper/2602.13855/) (2026)
- [Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation](https://mlsanity.com/paper/2603.21522/) (2026)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2605.23414/) (2026)
- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)
- [Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents](https://mlsanity.com/paper/2604.04131/) (2026)
- [Understanding Bugs in Modern Agentic Frameworks: A Study of Symptoms, Root Causes, and Triggering Conditions](https://mlsanity.com/paper/2604.08906/) (2026)
- [Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols](https://mlsanity.com/paper/2604.24512/) (2026)
- [When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors](https://mlsanity.com/paper/2604.21255/) (2026)
- [SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution](https://mlsanity.com/paper/2608.05573/) (2026)
- [Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference](https://mlsanity.com/paper/2607.02882/) (2026)
- [A Comprehensive Study of Implementation Bugs in Multi-modal Agents](https://mlsanity.com/paper/2607.04974/) (2026)

## Abstract (arXiv)

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the interactions, communication mechanisms, and failure causes within these systems. To bridge this gap, we present a benchmark of 34 representative programmable tasks designed to rigorously assess autonomous agents. Using this benchmark, we evaluate three popular open-source agent frameworks combined with two LLM backbones, observing a task completion rate of approximately 50%. Through in-depth failure analysis, we develop a three-tier taxonomy of failure causes aligned with task phases, highlighting planning errors, task execution issues, and incorrect response generation. Based on these insights, we propose actionable improvements to enhance agent planning and self-diagnosis capabilities. Our failure taxonomy, together with mitigation advice, provides an empirical foundation for developing more robust and effective autonomous agent systems in the future.