# RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement

arXiv: https://arxiv.org/abs/2607.25886 · HTML: https://mlsanity.com/paper/2607.25886/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Self-evolving LLM agents, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 9 of 9)

- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [AI4Research: A Survey of Artificial Intelligence for Scientific Research](https://mlsanity.com/paper/2507.01903/) (2025)
- [DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback](https://mlsanity.com/paper/2410.06215/) (2024)
- [Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?](https://mlsanity.com/paper/2604.10547/) (2026)
- [DCA-Bench: A Benchmark for Dataset Curation Agents](https://mlsanity.com/paper/2406.07275/) (2024)

## Built on by (most cited first, 18 of 18)

- [AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement](https://mlsanity.com/paper/2608.20318/) (2026)
- [HarnessOpt-Bench: Evaluating LLMs at Harness Optimization](https://mlsanity.com/paper/2608.06301/) (2026)
- [Aspire: Can Models Self-Evolve from Vague Goals?](https://mlsanity.com/paper/2608.31111/) (2026)
- [GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks](https://mlsanity.com/paper/2608.03764/) (2026)
- [What is Missing from AI Post-Training AI: An Empirical Analysis](https://mlsanity.com/paper/2608.19072/) (2026)
- [MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves](https://mlsanity.com/paper/2609.06396/) (2026)
- [Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Models](https://mlsanity.com/paper/2609.00768/) (2026)
- [EvalResearchBench: Can AI Agents Design Their Own Evaluations?](https://mlsanity.com/paper/2610.04184/) (2026)
- [SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?](https://mlsanity.com/paper/2609.09113/) (2026)
- [Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement](https://mlsanity.com/paper/2609.13406/) (2026)
- [AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?](https://mlsanity.com/paper/2609.35025/) (2026)
- [Imprint Reader: From Weight-Update Readout to Behavioral Intervention](https://mlsanity.com/paper/2609.35261/) (2026)
- [G"odel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement](https://mlsanity.com/paper/2609.36675/) (2026)
- [MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training](https://mlsanity.com/paper/2610.05398/) (2026)
- [RSIGym: A Flexible Environment for Recursive Self-Improvement](https://mlsanity.com/paper/2610.10310/) (2026)
- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)
- [MedEvo: Medical Reasoning Evolution through Knowledge Navigation](https://mlsanity.com/paper/2610.17690/) (2026)
- [ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution](https://mlsanity.com/paper/2610.17718/) (2026)

## Abstract (arXiv)

Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and validating training-data strategies, and learning from checkpoint feedback. Can LLM agents automate this loop? Existing benchmarks entangle research decisions with optimization, serving, evaluation, and systems implementation, obscuring agents' research capability. We introduce RSIBench-Data, a controlled benchmark of LLM agents as data-centric researchers with a fixed post-training stack. Agents iteratively revise training-data strategies for a fixed target model; training and serving use Tinker-backed services, official evaluation runs through Harbor and E2B sandboxes, and budgets are fixed across agents. We evaluate four frontier agents on six benchmarks across software engineering, terminal use, scientific question answering, and mathematics. Agents demonstrate core data-centric research capabilities: in 58.33% of settings, they improve upon the first valid attempt by refining strategies from feedback. However, improvement is inconsistent. Among searches continuing after the best observed score, 78.26% end with a lower-scoring final attempt, while the rest only recover the same peak. A strong candidate may therefore appear early or midway through a run even as later revisions fail. Trajectory analysis identifies four patterns in stronger runs: accurate hypotheses, validation-grounded supervision, behavior-aligned data, and preservation of strong checkpoints. These findings suggest that current agents can make useful data-centric discoveries but cannot yet translate feedback into consistent improvements. RSIBench-Data provides a measurable, auditable testbed for the research capabilities required for recursive self-improvement. We open-source our code at https://github.com/evolvent-ai/RSIBench-Data.