StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

• URL: http://arxiv.org/abs/2606.19613v1
• Date: Wed, 17 Jun 2026 21:36:09 GMT
• Title: StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns
• Abstract summary: We introduce StaminaBench, a benchmark that measures the stamina of coding agents.<n>Unlike the prevailing fraction-tasks metric, this matches real vibecoding where sessions run dozens or hundreds of turns.
• Score: 45.43677974796221
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

Related papers

• Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop Framework [0.3867363075280543]
  We present a closed-loop framework in which every accepted review comment is codified as a persistent behavioral rule.<n>The framework combines an accumulating rule set in a version-controlled instruction file, a self-review checklist, and automated validation.<n>We show that our framework achieves persistent cross-session learning without weight updates, operates on productions rather than synthetic benchmarks, and addresses an experiential dimension (behavioral consistency over time) that existing benchmarks do not measure.
  arXiv  Detail & Related papers  (2026-07-13T21:13:46Z)
• TTHE: Test-Time Harness Evolution [50.26245555541721]
  Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time.<n>We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs.<n>During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces.<n>A judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs.
  arXiv  Detail & Related papers  (2026-07-09T05:53:39Z)
• DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks [1.7623000586936592]
  DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents.<n>Its tasks are written from scratch across 91 active open-source repositories and five languages and are never contributed back upstream.<n>Despite being about half the length of SWE-Bench Pro's prompts, DeepSWE's prompts describe tasks whose reference solutions touch 5.5x more code.
  arXiv  Detail & Related papers  (2026-07-08T21:45:34Z)
• TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution [3.048952775453716]
  TestEvo-Bench is a benchmark of test and code co-evolution tasks mined from software repositories.<n>Each task is anchored to a real commit history and packaged with environment configuration.<n>Current snapshot contains 746 test generation and 509 test update tasks.
  arXiv  Detail & Related papers  (2026-07-02T17:35:20Z)
• WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation [88.10947115397971]
  This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories.<n>Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls.<n> Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification.
  arXiv  Detail & Related papers  (2026-05-11T17:49:43Z)
• Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution [20.606877071567958]
  We present TEBench, the first project-level benchmark for test evolution.<n>We construct TEBench through a four-stage pipeline over Defects4J projects.<n>We evaluate seven configurations spanning three industrial agent frameworks.
  arXiv  Detail & Related papers  (2026-05-07T12:31:09Z)
• ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents [77.22389710754452]
  We introduce bench, a benchmark for coworker agents built around multi-turn multi-day tasks.<n>The current release contains 100 tasks across 13 professional scenarios, executed against five stateful sandboxed services.<n>The strongest model reaches 75.8 weighted score, but the best strict Task Success is only 20.0%, indicating that partial progress is common.
  arXiv  Detail & Related papers  (2026-04-26T16:05:02Z)
• ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces [17.202580606345666]
  Large language model (LLM) agents are increasingly deployed to automate productivity tasks.<n>Existing benchmarks rely on simplified environments and fail to capture realistic, multi-service environments.<n>We introduce ClawsBench, a benchmark for evaluating and improving LLM agents in realistic productivity settings.
  arXiv  Detail & Related papers  (2026-04-06T21:09:06Z)
• Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning [54.95476453942411]
  Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates.<n>Recent self-play methods unify code and test generation in a single model.<n>Code-A1 achieves code generation performance matching or exceeding models trained on human-annotated tests.
  arXiv  Detail & Related papers  (2026-03-16T17:58:13Z)
• ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases [58.411135609139855]
  "Shortcuts" to complete tasks pose significant risks for reliable assessment and deployment of large language models.<n>We introduce ImpossibleBench, a benchmark framework that measures LLM agents' propensity to exploit test cases.<n>As a practical framework, ImpossibleBench is not just an evaluation but a versatile tool.
  arXiv  Detail & Related papers  (2025-10-23T06:58:32Z)
• CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation [10.048098631259876]
  Code generation aims to produce code that fulfills requirements written in natural languages automatically.<n>Large language Models (LLMs) like ChatGPT fail to ensure the syntactic and semantic correctness of the generated code.<n>We propose CodeCoR, a self-reflective multi-agent framework that evaluates the effectiveness of each agent and their collaborations.
  arXiv  Detail & Related papers  (2025-01-14T03:21:10Z)

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.