SelfImprove-Bench is an evaluation framework for recursively self‑improving (RSI) systems that organizes tasks into three core capabilities—Exploring, Planning, and Reasoning—using game‑based scenarios for controllability and reproducibility. It employs scalable task generation and orchestration driven by templates and difficulty coefficients, and introduces a generalization ladder (G0–G4) to assess how well performance gains transfer beyond training conditions. Experiments show that current RSI methods exhibit inconsistent evolutionary gains across these generalization levels.
arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.
The paper introduces ASPIRE, a benchmark that challenges language model agents to self‑evolve from vague, natural‑language goals without explicit evaluation metrics. In ASPIRE, agents must interpret the goal, select data and update strategies, and decide when to evaluate, all while the downstream tasks remain hidden. Experiments show that while agents can complete training loops, weight‑level improvements are sparse and unstable, and the best evolved harness still falls short of a strong engineered baseline.
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
The paper introduces Multi-Agent Self-Supervision (MASS), a recursive self‑improvement technique that alternates between evolutionary workflow optimization and supervised fine‑tuning on self‑generated multi‑agent trajectories. MASS enables a single base model to iteratively propose, execute, and self‑evaluate complex multi‑agent workflows, discovering effective roles and information routing. Experiments with Qwen3.6‑27B show 1.2–1.6× higher performance per output token on four open‑ended benchmarks, and student models trained on MASS traces outperform single‑agent students trained on 1.4× more tokens.
arXiv:2609.14857v1 Announce Type: new Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve executio...
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to...
arXiv:2610.14224v1 Announce Type: new Abstract: LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a pr...
arXiv:2610.29784v1 Announce Type: new Abstract: Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal syste...
arXiv:2609.37834v1 Announce Type: new Abstract: Harness optimization provides a practical setting for recursive self-improvement (RSI), where agent-generated modifications inform subsequent changes t...
arXiv:2607. 06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures.
SynCo is a data synthesis co‑training framework that enables self‑evolving large language models (LLMs) to improve autonomously. It employs two agents—a Synthesizer that generates training tasks based on the Reasoner’s evolving capabilities, and a Reasoner that learns from these tasks—using multi‑agent reinforcement learning to jointly optimize task quality and model performance. Experiments on eight mathematical reasoning benchmarks show that SynCo outperforms existing synthetic‑data methods, especially on previously unsolved problems.
arXiv:2606. 04455v1 Announce Type: new Abstract: Current AI benchmarks evaluate agents on task execution within human-designed workflows.