Heterogeneous Prompting and Execution Feedback for SWE Issue Test Generation and Selection
Not on the map. Why?
Abstract (arXiv)
A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically. The primary challenge in this setting is that the code to be tested is either missing or wrong, as evidenced by the existence of the issue in the first place. This has held back test generation for this setting: without the correct code to execute, it is difficult to leverage execution feedback to generate good tests. This paper introduces novel techniques for leveraging execution feedback to get around this problem, implemented in a new reproduction test generator called e-Otter++. Experiments show that e-Otter++ represents a leap ahead in the state-of-the-art for this problem, generating tests with an average fail-to-pass rate of 63% on the TDD-Bench Verified benchmark.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Aug 2025.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2025: 1; 2026: 9.
10 papers.
- 2025Investigating Test Overfitting on SWE-benchcited by 6
- 2026Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repaircited by 6
- 2026Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixescited by 3
- 2026ExecCritic: Learn to Test, Test to Improve for Coding Agentscited by 3
- 2026Resolving Java Code Repository Issues with iSWE Agentcited by 1
- 2026EvoOtter: Evolutionary Reproduction Test Generatorcited by 1
- 2026ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reportscited by 1
- 2026SWE-Spot: Building Small Repo-Experts with Repository-Centric Learningcited by 0
- 2026DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generationcited by 0
- 2026Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skillscited by 0
- 2026Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills10 Sep 2026
- 2026ExecCritic: Learn to Test, Test to Improve for Coding Agents8 Sep 2026
- 2026DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation24 Aug 2026
- 2026Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes22 Jul 2026
- 2026ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports10 Jul 2026
- 2026EvoOtter: Evolutionary Reproduction Test Generator3 Jul 2026
- 2026Resolving Java Code Repository Issues with iSWE Agent11 Mar 2026
- 2026SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning29 Jan 2026
- 2026Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair27 Jan 2026
- 2025Investigating Test Overfitting on SWE-bench20 Nov 2025