Search over Self-Edit Strategies for LLM Adaptation

• URL: http://arxiv.org/abs/2601.14532v1
• Date: Tue, 20 Jan 2026 22:59:58 GMT
• Title: Search over Self-Edit Strategies for LLM Adaptation
• Authors: Alistair Cheong, Haolin Cong, Tyler Yang, Dustin Miao,
• Abstract summary: This study investigates whether an LLM can use task feedback to decide how it should update its weights.<n>Using the Self-Adapting Language Models (SEAL) framework as a testbed, we relaxed its fixed human template constraint.<n>Two variants were studied, differing in whether template generation was conditioned on a lightweight archive of past templates.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many LLM-based open-ended search systems freeze the foundation model that proposes improvements to existing solutions, which may bottleneck long-run progress. Recent work has explored updating the proposal model at test time [arXiv:2511.23473], but the update strategy is still typically hand-specified. Therefore, this study investigated whether an LLM can use task feedback to decide how it should update its weights. For tractability, we focused on the simpler case where there is only one round of self-improvement, and restricted the update operator to self-supervised next token prediction (NTP), leaving the model freedom in choosing its training data and key NTP hyperparameters. Using the Self-Adapting Language Models (SEAL) [arXiv:2506.10943] framework as a testbed, we relaxed its fixed human template constraint and allowed the model to generate its own self-edit templates, thereby giving it more control over its training data and hyperparameters. Two variants were studied, differing in whether template generation was conditioned on a lightweight archive of past templates. In SEAL's Single-Passage Knowledge Incorporation setting with Qwen3-8B on SQuAD [arXiv:1606.05250], the no-archive variant performed comparably to the weaker "Implications" baseline, while the archive variant outperformed "Implications" and approached the strongest human-designed "Rewrite" baseline without surpassing it. Further analysis of collapse in the model's exploration revealed that a naive archive can confer some short-term robustness but can also accelerate homogenization, suggesting that explicit novelty pressure may be required to consistently advance beyond carefully optimized human strategies. Our code is available at https://github.com/cheongalc/search-self-edit-strategies .

Related papers

• MERGETUNE: Continued fine-tuning of vision-language models [77.8627788911249]
  Fine-tuning vision-language models (VLMs) often leads to catastrophic forgetting of pretrained knowledge.<n>We introduce a novel paradigm, continued fine-tuning (CFT), which seeks to recover pretrained knowledge after a zero-shot model has already been adapted.
  arXiv  Detail & Related papers  (2026-01-15T15:15:53Z)
• Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning [19.12792297140574]
  Continual learning aims to incrementally train a model on a sequence of tasks while retaining performance on prior ones.<n> storing and replaying data is often infeasible due to privacy or security constraints.<n>We propose Per-layer Model Inversion (PMI), inspired by faster convergence in single-layer optimization.
  arXiv  Detail & Related papers  (2025-10-30T09:58:48Z)
• Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future [38.1810626252963]
  Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting.<n>We propose textbf Self-Rewarding Language Models that strategically coordinate past, present, and future model generations to sustain learning signals.
  arXiv  Detail & Related papers  (2025-08-08T05:25:54Z)
• Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach [65.6966065843227]
  Iterative Reweight-then-IRO is a framework that performs RL-style alignment of a frozen base model without touching its parameters.<n>At test time, the value functions are used to guide the base model generation via a search-based optimization process.<n> Notably, users can apply IRO to align a model on their own dataset, similar to OpenAI's reinforcement fine-tuning (RFT)
  arXiv  Detail & Related papers  (2025-06-21T21:49:02Z)
• Self-Adapting Language Models [47.52508465862889]
  Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples.<n>We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives.<n> Experiments on knowledge incorporation and few-shot generalization show that SEAL is a promising step toward language models capable of self-directed adaptation.
  arXiv  Detail & Related papers  (2025-06-12T17:48:13Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Test-Time Model Adaptation with Only Forward Passes [68.11784295706995]
  Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. We propose a test-time Forward-Optimization Adaptation (FOA) method. FOA runs on quantized 8-bit ViT, outperforms gradient-based TENT on full-precision 32-bit ViT, and achieves an up to 24-fold memory reduction on ImageNet-C.
  arXiv  Detail & Related papers  (2024-04-02T05:34:33Z)
• AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation [1.4530711901349282]
  We propose to validate test-time adaptation methods using datasets for autonomous driving, namely CLAD-C and SHIFT. We observe that current test-time adaptation methods struggle to effectively handle varying degrees of domain shift. We enhance the well-established self-training framework by incorporating a small memory buffer to increase model stability.
  arXiv  Detail & Related papers  (2023-09-18T19:34:23Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)

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.