#artificial intelligence #machine learning #natural language processing Preprint

On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification

Qinyuan Ye Yu Li Yada Pruksachatkun Jiaxin Zhang Chien-Sheng Wu

Aug 2026 · 1 citation · 68 references

Computer Science

TL;DR

A comprehensive re-evaluation of two memory-based methods for self-improving agents is conducted, broadening the scope of evaluation along two axes and hypothesizing that task and environment underspecification contribute to this fragility.

Abstract

Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods have been critically overlooked. In this work, we conduct a comprehensive re-evaluation of two memory-based methods, broadening the scope of evaluation along two axes: (1) including multiple runs to quantify variance, and (2) randomly shuffling the tasks to investigate the effect of task order. Through these experiments, we make two observations that expose the fragility of current methods: First, agent evaluation is inherently noisy in complex environments and on multi-step tasks, and stacking a self-improving loop on top can further amplify this noise. Second, the agent's improvement is highly dependent on task order. Prior works often adopt default orderings that impose an implicit curriculum, acting as a hidden prerequisite for success. To better understand this fragility, we manually examine the agents'memory and hypothesize that task and environment underspecification contribute to this fragility. We validate this hypothesis by incorporating information that enables better specification, such as detailed rubrics and environment feedback, into the memory construction process. While this added information partially closes the performance degradation in previous experiments, significant gaps still remain, suggesting that other uncharacterized factors contribute to this fragility. Looking ahead, our work advocates for more rigorous evaluation protocols for self-improving agents by reporting results across multiple runs and stress-testing them under challenging conditions. Moreover, our findings on underspecification call for systems and interfaces that enable effective human oversight, preventing agents from failing in unforeseeable ways.

arXiv Semantic Scholar

View source

Similar papers

Preprint Aug 2026

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

The PAST-Bench benchmark is introduced, a benchmark designed to isolate how persistent agents can progress from retaining experience to systematically improving through it, and Hermes+ is developed, which raises the average gain from retained experience and provides clearer pathway evidence.

Shuhan Xue, Zixin Ding, Yi-Jun Shen et al. · 2 citations

Book Open access Jul 2026

Is a Busy Search Agent a Good One? Overthinking and Overretrieval at Scale

This work conducts a systematic study of overthinking and overretrieval in search agents from a scaling perspective and proposes a lightweight post-hoc reflection framework that converts the proposed evaluation signals into explicit feedback rewards to guide agents' reasoning trajectories.

Xin Liu, Ruqing Zhang, Yu-An Liu et al. · Annual International ACM SIG... · 0 citations

Preprint Aug 2026

Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation

This work reproduces SDPO's reported gains in its easy setting, then applies the identical setup to difficult tasks and finds that it does not teach anything, and explains this failure through a single causal chain from the loss to the model it produces.

Sarthak Harne, Chinmay Karkar, Yash Pandya et al. · 1 citation

Preprint Aug 2026

From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation

NIS-Agent is proposed, which applies context isolation at the two decision points most vulnerable to inertia bias: webpage triage and final-answer validation, and trains an 8B model to be intrinsically more resistant to inertia bias.

Xiangdong Zhang, Zhanwei Zhang, Zhihang Fu et al. · 0 citations

Preprint Aug 2026

Demystifying Agent Skills: Why They Work-Until They Don't

This work designs a contrastive study that combines controlled quantitative experiments with paired trajectory analysis and consolidates observations into a taxonomy of three high-level categories and twelve skill-use modes, showing that skills work when noisy trajectories become procedural anchors that stabilize execution.

Zhiyuan Jiang, Fan Huang, Hanwen Xing et al. · 0 citations

Preprint Aug 2026

PATH-Bench: Path-Dependent Evaluation of Lifelong Agents

Lifelong LLM agents increasingly adapt through external learning states that store past interactions as retrievable memories or reusable skills, yet existing benchmarks rarely account for how the path of accumulated experience shapes what agents transfer and retain. In this work, we establish PATH-Bench, a benchmark for path-dependent evaluation of lifelong agents. PATH-Bench estimates directed task relationships via multi-model in-context learning, constructs probe-centered sequences with controlled helpful and interfering histories, and repeatedly evaluates probe tasks to measure average performance, forward transfer, backward transfer, and forgetting. We evaluate eight representative agents on single-turn code generation and multi-turn tool-use tasks under positive- and negative-dominant histories. Benchmark results show that experience utility depends jointly on how experience is represented and on the task's interaction structure, that strong transfer does not ensure retention, and that later experience can reshape gains acquired earlier in the learning path. Based on these findings, we propose Selective Experience Use (SEU), an agent harness that regulates how path-accumulated experience influences each new task, admitting helpful items while filtering out potential interference. SEU consistently reduces forgetting while improving forward transfer in the majority of settings. The PATH-Bench provides both a controlled evaluation framework and actionable guidance for designing more selective and robust lifelong agents.

Xidong Yang, Xingyi Zhang, Wenhao Li et al. · 0 citations