# Agent-Based Test Assertion Generation via Diverse Perspective Aggregation

arXiv: https://arxiv.org/abs/2608.05822 · HTML: https://mlsanity.com/paper/2608.05822/

## 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 22 of its 50 references that are in the map.
- First posted on arXiv 6 Aug 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, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Unit Test Case Generation with Transformers and Focal Context](https://mlsanity.com/paper/2009.05617/) (2020)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives](https://mlsanity.com/paper/2401.02009/) (2024)
- [TOGA: A Neural Method for Test Oracle Generation](https://mlsanity.com/paper/2109.09262/) (2021)
- [On Learning Meaningful Assert Statements for Unit Test Cases](https://mlsanity.com/paper/2002.05800/) (2020)
- [A Survey of Symbolic Execution Techniques](https://mlsanity.com/paper/1610.00502/) (2016)
- [On the Evaluation of Large Language Models in Unit Test Generation](https://mlsanity.com/paper/2406.18181/) (2024)
- [Learning Deep Semantics for Test Completion](https://mlsanity.com/paper/2302.10166/) (2023)
- [TOGLL: Correct and Strong Test Oracle Generation with LLMs](https://mlsanity.com/paper/2405.03786/) (2024)
- [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024)
- [Fixing Large Language Models' Specification Misunderstanding for Better Code Generation](https://mlsanity.com/paper/2309.16120/) (2023)
- [AsserT5: Test Assertion Generation Using a Fine-Tuned Code Language Model](https://mlsanity.com/paper/2502.02708/) (2025)
- [Large Language Models for Equivalent Mutant Detection: How Far Are We?](https://mlsanity.com/paper/2408.01760/) (2024)
- [Revisiting and Improving Retrieval-Augmented Deep Assertion Generation](https://mlsanity.com/paper/2309.10264/) (2023)
- [Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models](https://mlsanity.com/paper/2502.16071/) (2025)
- [Clarifying Semantics of In-Context Examples for Unit Test Generation](https://mlsanity.com/paper/2510.01994/) (2025)
- [Variable-Based Fault Localization via Enhanced Decision Tree](https://mlsanity.com/paper/2211.11526/) (2022)

## Abstract (arXiv)

Test assertions are critical elements of unit tests, serving as checkpoints to validate expected behavior and ensure software correctness. Numerous techniques have been proposed to automate assertion generation, with recent progress notably driven by large language models (LLMs). Despite the promise, existing approaches such as ChatAssert suffer from modest accuracy, heavy reliance on oversampling, and vulnerability to model randomness due to one-shot prompting. To address these limitations, we propose AssertMate, a novel agent-based assertion generation framework that enhances the quality and reliability of LLM-generated assertions through three key components: (1) actual value construction that identifies assertion targets via static analysis and type-aware heuristics; (2) multi-perspective expected value prediction using code generation, retrieval-augmented generation (RAG), and chain-of-thought (CoT) reasoning agents; and (3) an LLM-as-a-Judge collaboration mechanism to select the most appropriate assertion. Evaluation on the Defects4J benchmark demonstrates that AssertMate significantly outperforms state-of-the-art techniques in compilation success and pass rates, along with substantially higher bug detection capabilities. Integration with EvoSuite further validates AssertMate's practicality, yielding superior mutation coverage and kill counts. Ablation studies reveal that each of the three components makes a significant and complementary contribution to the overall performance. This work affirms the great potential of aggregating diverse perspectives to enhance the effectiveness of LLM-based assertion generation.