Self-Improving LLM Agents at Test-Time

• URL: http://arxiv.org/abs/2510.07841v1
• Date: Thu, 09 Oct 2025 06:37:35 GMT
• Title: Self-Improving LLM Agents at Test-Time
• Authors: Emre Can Acikgoz, Cheng Qian, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur,
• Abstract summary: One paradigm of language model (LM) fine-tuning relies on creating large training datasets.<n>In practice, gathering large sets of data is inefficient, and training on them is prohibitively expensive.<n>We study two variants of this approach: Test-Time Self-Improvement (TT-SI) and Test-Time Distillation (TT-D)
• Score: 49.9396634315896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize to novel tasks after post-training. In practice, gathering large sets of data is inefficient, and training on them is prohibitively expensive; worse, there is no guarantee that the resulting model will handle complex scenarios or generalize better. Moreover, existing techniques rarely assess whether a training sample provides novel information or is redundant with the knowledge already acquired by the model, resulting in unnecessary costs. In this work, we explore a new test-time self-improvement method to create more effective and generalizable agentic LMs on-the-fly. The proposed algorithm can be summarized in three steps: (i) first it identifies the samples that model struggles with (self-awareness), (ii) then generates similar examples from detected uncertain samples (self-data augmentation), and (iii) uses these newly generated samples at test-time fine-tuning (self-improvement). We study two variants of this approach: Test-Time Self-Improvement (TT-SI), where the same model generates additional training examples from its own uncertain cases and then learns from them, and contrast this approach with Test-Time Distillation (TT-D), where a stronger model generates similar examples for uncertain cases, enabling student to adapt using distilled supervision. Empirical evaluations across different agent benchmarks demonstrate that TT-SI improves the performance with +5.48% absolute accuracy gain on average across all benchmarks and surpasses other standard learning methods, yet using 68x less training samples. Our findings highlight the promise of TT-SI, demonstrating the potential of self-improvement algorithms at test-time as a new paradigm for building more capable agents toward self-evolution.

Related papers

• Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection [6.471199527741301]
  We introduce a new framework called VDS-TTT - Verifier-Driven Sample Selection for Test-Time Training.<n>We use a learned verifier to score a pool of generated responses and select only from high ranking pseudo-labeled examples for fine-tuned adaptation.<n>We fine-tune only low-rank LoRA adapter parameters, ensuring adaptation efficiency and fast convergence.
  arXiv  Detail & Related papers  (2025-05-26T03:54:47Z)
• Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples [62.13094877228772]
  We show that mislabeled examples correctly predicted by the model early in the training process are particularly harmful to model performance.<n>We propose Early Cutting, which employs the model's later training state to re-select the confident subset identified early in training.
  arXiv  Detail & Related papers  (2025-02-12T09:12:45Z)
• Iterative Deepening Sampling as Efficient Test-Time Scaling [27.807695570974644]
  Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks.<n>We propose a novel iterative deepening sampling algorithm framework designed to enhance self-correction and generate higher-quality samples.
  arXiv  Detail & Related papers  (2025-02-08T04:39:51Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Re-ReST: Reflection-Reinforced Self-Training for Language Agents [101.22559705696885]
  Self-training in language agents can generate supervision from the agent itself.<n>We present Reflection-Reinforced Self-Training (Re-ReST), which uses a textitreflector to refine low-quality generated samples.
  arXiv  Detail & Related papers  (2024-06-03T16:21:38Z)
• Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning [17.980649681325406]
  We present Point-TTA, a novel test-time adaptation framework for point cloud registration (PCR) Our model can adapt to unseen distributions at test-time without requiring any prior knowledge of the test data. During training, our model is trained using a meta-auxiliary learning approach, such that the adapted model via auxiliary tasks improves the accuracy of the primary task.
  arXiv  Detail & Related papers  (2023-08-31T06:32:11Z)
• Test-Time Adaptation with Perturbation Consistency Learning [32.58879780726279]
  We propose a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts. Our method can achieve higher or comparable performance with less inference time over strong PLM backbones.
  arXiv  Detail & Related papers  (2023-04-25T12:29:22Z)
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [117.72709110877939]
  Test-time adaptation (TTA) has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.<n>We categorize TTA into several distinct groups based on the form of test data, namely, test-time domain adaptation, test-time batch adaptation, and online test-time adaptation.
  arXiv  Detail & Related papers  (2023-03-27T16:32:21Z)
• Are Sample-Efficient NLP Models More Robust? [90.54786862811183]
  We investigate the relationship between sample efficiency (amount of data needed to reach a given ID accuracy) and robustness (how models fare on OOD evaluation) We find that higher sample efficiency is only correlated with better average OOD robustness on some modeling interventions and tasks, but not others. These results suggest that general-purpose methods for improving sample efficiency are unlikely to yield universal OOD robustness improvements, since such improvements are highly dataset- and task-dependent.
  arXiv  Detail & Related papers  (2022-10-12T17:54:59Z)
• TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision [70.05605071885914]
  We propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples. We show the success of our method on the common benchmark dataset CIFAR10-C.
  arXiv  Detail & Related papers  (2022-05-18T05:43:06Z)
• Efficient Test-Time Model Adaptation without Forgetting [60.36499845014649]
  Test-time adaptation seeks to tackle potential distribution shifts between training and testing data. We propose an active sample selection criterion to identify reliable and non-redundant samples. We also introduce a Fisher regularizer to constrain important model parameters from drastic changes.
  arXiv  Detail & Related papers  (2022-04-06T06:39:40Z)
• Uncertainty Estimation for Language Reward Models [5.33024001730262]
  Language models can learn a range of capabilities from unsupervised training on text corpora. It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons. We seek to address these problems via uncertainty estimation, which can improve sample efficiency and robustness using active learning and risk-averse reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-14T20:13:21Z)

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.