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

• URL: http://arxiv.org/abs/2607.25886v1
• Date: Tue, 28 Jul 2026 15:46:41 GMT
• Title: RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
• Abstract summary: Existing benchmarks entangle research decisions with optimization, serving, evaluation, and systems implementation.<n>We introduce RSIBench-Data, a benchmark of LLM agents as data-centric researchers with a fixed post-training stack.<n>We evaluate four frontier agents on six benchmarks across software engineering, terminal use, scientific question answering, and mathematics.
• Score: 27.641105176473136
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• Can Generalist Agents Automate Data Curation? [58.652262227632406]
  Curating training data is among the most consequential yet labor-intensive parts of modern AI development.<n>We ask whether generalist coding agents can automate this data-curation loop.<n>We introduce *Curation-Bench*, an agent-centric benchmark that fixes the model, training recipe, and evaluation suite.
  arXiv  Detail & Related papers  (2026-06-02T22:26:53Z)
• Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents? [15.605151408619895]
  We present a controlled empirical study that isolates three under-explored dimensions of search agent training.<n>First, we identify a critical data-coverage issue in the widely used Wikipedia 2018 corpus and show that correcting it alone yields larger gains than the differences between training algorithms.<n>Second, we systematically compare outcome-based and process-based reward methods across three base models, finding that the simplest outcome-based approach achieves competitive or superior performance in most settings.<n>Third, we analyze training data diversity, off-policy data utilization, and search budget scaling, distilling practical guidelines for training effective search agents.
  arXiv  Detail & Related papers  (2026-05-27T03:04:36Z)
• Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis [68.28714988482703]
  Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs)<n>We present a study revealing that general-domain PRMs struggle to supervise data analysis agents.<n>We introduce DataPRM, a novel environment-aware generative process reward model.
  arXiv  Detail & Related papers  (2026-04-27T09:00:30Z)
• A Rubric-Supervised Critic from Sparse Real-World Outcomes [87.11204512676193]
  Real-world coding agents operate with humans in the loop, where success signals are typically noisy, delayed, and sparse.<n>We propose a process to learn a "critic" model from sparse and noisy interaction data, which can then be used both as a reward model for either RL-based training or inference-time scaling.
  arXiv  Detail & Related papers  (2026-03-04T07:23:54Z)
• Learning to Detect Language Model Training Data via Active Reconstruction [65.4791582049743]
  We introduce textbfActive Data Reconstruction Attack (ADRA)<n>ADRA induces a model to reconstruct a given text through training.<n>Our algorithms consistently outperform existing MIAs in detecting pre-training, post-training, and distillation data.
  arXiv  Detail & Related papers  (2026-02-22T03:20:06Z)
• Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification [71.98473277917962]
  Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving.<n>We propose an alternative paradigm: self-evolving the agent's ability by iteratively verifying the policy model's outputs, guided by meticulously crafted rubrics.<n>We present DeepVerifier, a rubrics-based outcome reward verifier that leverages the asymmetry of verification.
  arXiv  Detail & Related papers  (2026-01-22T09:47:31Z)
• Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains [97.5573252172065]
  We train a family of Automatic Reasoning Evaluators (FARE) with a simple iterative rejection-sampling supervised finetuning approach.<n>FARE-8B challenges larger specialized RL-trained evaluators and FARE-20B sets the new standard for open-source evaluators.<n>As inference-time rerankers, FARE-20B achieves near-oracle performance on MATH.
  arXiv  Detail & Related papers  (2025-10-20T17:52:06Z)
• Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training [18.896813839389893]
  We propose an iterative self-training framework, Agent-R, that enables language Agent to Reflect on the fly.<n>Unlike traditional methods that reward or penalize actions based on correctness, Agent-R leverages MCTS to construct training data that recover correct trajectories from erroneous ones.<n>Our findings demonstrate that Agent-R continuously improves the model's ability to recover from errors and enables timely error correction.
  arXiv  Detail & Related papers  (2025-01-20T11:46:04Z)
• Solving Offline Reinforcement Learning with Decision Tree Regression [0.0]
  This study presents a novel approach to addressing offline reinforcement learning problems by reframing them as regression tasks. We introduce two distinct frameworks: return-conditioned and return-weighted decision tree policies. Despite the simplification inherent in this reformulated approach to offline RL, our agents demonstrate performance that is at least on par with the established methods.
  arXiv  Detail & Related papers  (2024-01-21T23:50:46Z)

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.