arXiv AI

Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks

arXiv AI
Nov 6

Beneath the Surface: What We Overlook When We Talk About Agent Evolution

The paper investigates how agent harness evolution supports recursive self‑improvement without changing model weights, assessing four methods across general and coding tasks. Repeated tests and component interventions show that all evolved agents acquire new tasks while losing some previously mastered ones, with reliability gains sometimes offset by higher deployment costs. The study highlights that the highest‑scoring agent does not always deliver the greatest mean improvement, and that stricter admission criteria can eliminate useful alternatives; it proposes preservation‑aware evaluation and a follow‑up tool, EvoAudit, to refine agent design.

By Xiaobo Wang, Zimu Wang, Siyu Ye, Jiaqi Li, Min Tang, Jun Bai, Yuling Shi, Ruobing Wang, Jingjing Zhang, Chaofan Wang, Kai Wu, Mengnan Qi, Kai Cai, Xiaodong Gu, Qi Liu, Zilong Zheng
arXiv Machine Learning
6d ago

The RSI Tax: When Recursive Self-Improvement Is Not Worth the Cost

The paper introduces the concept of the RSI Tax, the token cost incurred during recursive self‑improvement (RSI) of language‑model agents. By evaluating six RSI methods on continual task streams, the authors find that a bounded‑note baseline can match or surpass the performance of more complex methods while saving 65.6–71.0% of total tokens. The study decomposes the RSI Tax into verification, exploration, and writing costs, revealing that verification dominates the expense and that much of the cost is tied to unused states or artifacts, highlighting a practical limitation of costly RSI procedures.

By Yitong Zhang, Ang Li, Yisen Wang
arXiv AI
Oct 26

RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training

RSI-Opt introduces Recursive Self-Improvement Optimizer Agents that evolve their own training policies by accumulating knowledge from previous runs, including prompts, playbooks, optimizer code, and decision cadences. A meta‑agent rewrites and archives these policies, enabling reusable procedures and code that adapt to new tasks. Across multiple generations and tasks, RSI‑Opt improves optimizer performance, achieving higher z‑scores on evolution suites, better cross‑model transfer, and significant error reductions on PDE benchmarks compared to fixed‑prompt baselines.

By Binghang Lu, Yige Sun, Guang Lin
arXiv AI
Oct 5

VERSE: Verified Self-Evolving Optimizer for Agent Harnesses

The paper introduces VERSE, a Verified Self‑Evolving optimizer that enhances LLM agent harnesses by allowing the optimizer to test edits, replay failures, and perturb steps while tracking fixes and regressions. VERSE builds its own tools for failure analysis, verification, training audits, and workflow control, and uses this feedback to revise the harness’s prompts, skills, tools, hooks, and notes without changing model weights. In experiments across five executors and multiple languages, VERSE improves all evaluated harness optimizers, achieving higher accuracy on held‑out and out‑of‑distribution tasks compared to the strongest baselines.

By Zekai Wang, Yingqiang Ge, Zekun Wang, Hai Wang, Yuhui Xu, Joshua Frandsen, Shancong Fu, Ashia C. Wilson, Chandan K. Reddy
arXiv AI
Jun 26

The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators

arXiv:2606. 26294v1 Announce Type: cross Abstract: Self-improving agents are state-of-the-art (SOTA) on agentic coding benchmarks and have recently been extended to general domains.

By Alex Iacob, Andrej Jovanovi\'c, William F. Shen, Daniel Burkhardt, Meghdad Kurmanji, Nurbek Tastan, Lorenzo Sani, Niccol\`o Alberto Elia Venanzi, Ambroise Odonnat, Zeyu Cao, Bill Marino, Xinchi Qiu, Nicholas D. Lane
arXiv AI
6d ago

Veritas: A Verifier Generation Harness for Agent Tasks

Veritas is a harness that automatically generates verifiers for agent tasks, adding an evidence header, a library of domain rules, and authoring principles refined through a self‑improvement loop. It was evaluated on six benchmarks, outperforming seven other harnesses on all four execution‑scored tasks and matching or exceeding performance on pairwise comparison tasks. The system also improves agreement with official verdicts across multiple model families and harness‑benchmark pairs.

By Daoan Zhang, Qinbo Bai, Dehai Min, Xingyu Mu, Ziyi Chen, Jianing Yin
arXiv AI
Oct 19

EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?

EvalResearchBench (ERB) is a benchmark that tests whether AI agents can autonomously design evaluation tasks for recursive self‑improvement. In ERB, a researcher agent selects or synthesizes tasks, builds graders, and refines them through pilot tests before producing a final evaluator that runs within fixed time and API budgets. Experiments with nine researchers and thirteen candidate models show that the best automated evaluators achieve about 75% concordance with target benchmarks, below the 91% ceiling set by target disagreements, and that human‑designed task samples still outperform many automated approaches.

By Yaolun Zhang, Tianyi Xu, Yujie Zhao, Jishen Zhao, Qingyun Wu, Huazheng Wang