PyTorchKR Papers

“Code Generation”

총 10,140편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2408.02635공식 코드 · Papers with Code

Interactive 3D Medical Image Segmentation with SAM 2

Interactive medical image segmentation (IMIS) has shown significant potential in enhancing segmentation accuracy by integrating iterative feedback from medical professionals. However, the limited availability of enough 3D medical data restricts the generalization and robustness of most IMIS methods. The Segment Anything Model (SAM), though effective for 2D images, requires expensive semi-auto slice-by-slice annotations for 3D medical images. In this paper, we explore the zero-shot capabilities of SAM 2, the next-generation Meta SAM model trained on videos, for 3D medical image segmentation. By treating sequential 2D slices of 3D images as video frames, SAM 2 can fully automatically propagate annotations from a single frame to the entire 3D volume. We propose a practical pipeline for using SAM 2 in 3D medical image segmentation and present key findings highlighting its efficiency and potential for further optimization. Concretely, numerical experiments on the BraTS2020 and the medical segmentation decathlon datasets demonstrate that SAM 2 still has a gap with supervised methods but can narrow the gap in specific settings and organ types, significantly reducing the annotation burden on medical professionals. Our code will be open-sourced and available at https://github.com/Chuyun-Shen/SAM_2_Medical_3D.

arXiv:2408.10923공식 코드 · Papers with Code

LBC: Language-Based-Classifier for Out-Of-Variable Generalization

Large Language Models (LLMs) have great success in natural language processing tasks such as response generation. However, their use in tabular data has been limited due to their inferior performance compared to traditional machine learning models (TMLs) such as XGBoost. We find that the pre-trained knowledge of LLMs enables them to interpret new variables that appear in a test without additional training, a capability central to the concept of Out-of-Variable (OOV). From the findings, we propose a Language-Based-Classifier (LBC), a classifier that maximizes the benefits of LLMs to outperform TMLs on OOV tasks. LBC employs three key methodological strategies: 1) Categorical changes to adjust data to better fit the model's understanding, 2) Advanced order and indicator to enhance data representation to the model, and 3) Using verbalizer to map logit scores to classes during inference to generate model predictions. These strategies, combined with the pre-trained knowledge of LBC, emphasize the model's ability to effectively handle OOV tasks. We empirically and theoretically validate the superiority of LBC. LBC is the first study to apply an LLM-based model to OOV tasks. The source code is at https://github.com/sksmssh/LBCforOOVGen

arXiv:2410.18737

Rectified Diffusion Guidance for Conditional Generation

Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion model sampling. Theoretically, however, denoising with CFG cannot be expressed as a reciprocal diffusion process, which may consequently leave some hidden risks during use. In this work, we revisit the theory behind CFG and rigorously confirm that the improper configuration of the combination coefficients (i.e., the widely used summing-to-one version) brings about expectation shift of the generative distribution. To rectify this issue, we propose ReCFG with a relaxation on the guidance coefficients such that denoising with ReCFG strictly aligns with the diffusion theory. We further show that our approach enjoys a closed-form solution given the guidance strength. That way, the rectified coefficients can be readily pre-computed via traversing the observed data, leaving the sampling speed barely affected. Empirical evidence on real-world data demonstrate the compatibility of our post-hoc design with existing state-of-the-art diffusion models, including both class-conditioned ones (e.g., EDM2 on ImageNet) and text-conditioned ones (e.g., SD3 on CC12M), without any retraining. We will open-source the code to facilitate further research.

arXiv:2411.01030공식 코드 · Papers with Code

Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula

Efficient state space models (SSMs), such as linear recurrent neural networks and linear attention variants, offer computational advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text copying, associative recall, and question answering over long contexts. Previous efforts to address these challenges have focused on architectural modifications, often reintroducing computational inefficiencies. In this paper, we propose a novel training procedure, Birdie, that significantly enhances the in-context retrieval capabilities of SSMs without altering their architecture. Our approach combines bidirectional input processing with dynamic mixtures of specialized pre-training objectives, optimized via reinforcement learning. We introduce a new bidirectional SSM architecture that seamlessly transitions from bidirectional context processing to causal generation. Experimental evaluations demonstrate that Birdie markedly improves performance on retrieval-intensive tasks such as multi-number phone book lookup, long paragraph question-answering, and infilling. This narrows the performance gap with Transformers, while retaining computational efficiency. Our findings highlight the importance of training procedures in leveraging the fixed-state capacity of SSMs, offering a new direction to advance their capabilities. All code and pre-trained models are available at https://www.github.com/samblouir/birdie, with support for JAX and PyTorch.

arXiv:2411.01142

NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference

Online LLM inference powers many exciting applications such as intelligent chatbots and autonomous agents. Modern LLM inference engines widely rely on request batching to improve inference throughput, aiming to make it cost-efficient when running on expensive GPU accelerators. However, the limited GPU memory has largely limited the batch size achieved in practice, leaving significant GPU compute resources wasted. We present NEO, an online LLM inference system that offloads part of attention compute and KV cache states from the GPU to the local host CPU, effectively increasing the GPU batch size and thus inference throughput. To this end, NEO proposes asymmetric GPU-CPU pipelining and load-aware scheduling to balance GPU and CPU loads and fully utilize their compute and memory resources. We evaluate NEO on a wide range of workloads (i.e., code generation, text summarization), GPUs (i.e., T4, A10G, H100), and LLM models (i.e., 7B, 8B, 70B). NEO achieves up to 7.5$\times$, 26%, and 14% higher throughput compared to GPU-only approach on T4, A10G, and H100 GPUs, respectively, while maintaining the same latency; with more powerful CPUs, NEO achieves up to 79.3% throughput gain on A10G GPU.

논문 ID: document/1073201

Enhancing GANs with MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition

Generative Adversarial Networks (GANs) have gained considerable attention owing to their impressive ability to generate high-quality, realistic images from a desired data distribution. This research introduces advancements in GANs by developing an improved activation function, a novel training strategy, and an adaptive rank decomposition method to compress the network. The proposed activation function, called Parametric Mish (PMish), automatically adjusts a trainable parameter to control the smoothness and shape of the activation function. Our method employs a Neural Architecture Search (NAS) to discover the optimal architecture for image generation while using the Maximum Mean Discrepancy (MMD) repulsive loss for adversarial training. The proposed novel training strategy improves performance by progressively increasing the upper bound of the bounded MMD-GAN repulsive loss. Finally, the proposed Adaptive Rank Decomposition (ARD) method reduces the complexity of the network with minimal impact on its generative performance, thus enabling efficient deployment on resource-limited platforms. The effectiveness of these advancements is rigorously tested on standard benchmark datasets such as CIFAR-10, CIFAR-100, STL-10, and CelebA, where significant improvements over existing techniques are demonstrated. The implementation code is available at: https://github.com/PrasannaPulakurthi/MMD-PMish-NAS

arXiv:2412.05628공식 코드 · Papers with Code

Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising

Transformer-based diffusion models have achieved significant advancements across a variety of generative tasks. However, producing high-quality outputs typically necessitates large transformer models, which result in substantial training and inference overhead. In this work, we investigate an alternative approach involving multiple experts for denoising, and introduce Remix-DiT, a novel method designed to enhance output quality at a low cost. The goal of Remix-DiT is to craft N diffusion experts for different denoising timesteps, yet without the need for expensive training of N independent models. To achieve this, Remix-DiT employs K basis models (where K < N) and utilizes learnable mixing coefficients to adaptively craft expert models. This design offers two significant advantages: first, although the total model size is increased, the model produced by the mixing operation shares the same architecture as a plain model, making the overall model as efficient as a standard diffusion transformer. Second, the learnable mixing adaptively allocates model capacity across timesteps, thereby effectively improving generation quality. Experiments conducted on the ImageNet dataset demonstrate that Remix-DiT achieves promising results compared to standard diffusion transformers and other multiple-expert methods. The code is available at https://github.com/VainF/Remix-DiT.

arXiv:2412.12737v3cs.CV공식 코드 · Papers with Code

PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model

PolSAR data presents unique challenges due to its rich and complex characteristics. Existing data representations, such as complex-valued data, polarimetric features, and amplitude images, are widely used. However, these formats often face issues related to usability, interpretability, and data integrity. Most feature extraction networks for PolSAR are small, limiting their ability to capture features effectively. To address these issues, We propose the Polarimetric Scattering Mechanism-Informed SAM (PolSAM), an enhanced Segment Anything Model (SAM) that integrates domain-specific scattering characteristics and a novel prompt generation strategy. PolSAM introduces Microwave Vision Data (MVD), a lightweight and interpretable data representation derived from polarimetric decomposition and semantic correlations. We propose two key components: the Feature-Level Fusion Prompt (FFP), which fuses visual tokens from pseudo-colored SAR images and MVD to address modality incompatibility in the frozen SAM encoder, and the Semantic-Level Fusion Prompt (SFP), which refines sparse and dense segmentation prompts using semantic information. Experimental results on the PhySAR-Seg datasets demonstrate that PolSAM significantly outperforms existing SAM-based and multimodal fusion models, improving segmentation accuracy, reducing data storage, and accelerating inference time. The source code and datasets will be made publicly available at https://github.com/XAI4SAR/PolSAM.

arXiv:2412.13871공식 코드 · Papers with Code

LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer

In multimodal large language models (MLLMs), vision transformers (ViTs) are widely employed for visual encoding. However, their performance in solving universal MLLM tasks is not satisfactory. We attribute it to a lack of information from diverse visual levels, impeding alignment with the various semantic granularity required for language generation. To address this issue, we present LLaVA-UHD v2, an advanced MLLM centered around a Hierarchical window transformer that enables capturing diverse visual granularity by constructing and integrating a high-resolution feature pyramid. As a vision-language projector, Hiwin transformer comprises two primary modules: (i) an inverse feature pyramid, constructed by a ViT-derived feature up-sampling process utilizing high-frequency details from an image pyramid, and (ii) hierarchical window attention, focusing on a set of key sampling features within cross-scale windows to condense multi-level feature maps. Extensive experiments demonstrate that LLaVA-UHD v2 achieves superior performance over existing MLLMs on popular benchmarks. Notably, our design brings an average boost of 3.7% across 14 benchmarks compared with the baseline method, 9.3% on DocVQA for instance. We make all the data, model checkpoint, and code publicly available to facilitate future research.

arXiv:2502.04318

sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views

Reconstructing unbounded outdoor scenes from sparse outward-facing views poses significant challenges due to minimal view overlap. Previous methods often lack cross-scene understanding and their primitive-centric formulations overload local features to compensate for missing global context, resulting in blurriness in unseen parts of the scene. We propose sshELF, a fast, single-shot pipeline for sparse-view 3D scene reconstruction via hierarchal extrapolation of latent features. Our key insights is that disentangling information extrapolation from primitive decoding allows efficient transfer of structural patterns across training scenes. Our method: (1) learns cross-scene priors to generate intermediate virtual views to extrapolate to unobserved regions, (2) offers a two-stage network design separating virtual view generation from 3D primitive decoding for efficient training and modular model design, and (3) integrates a pre-trained foundation model for joint inference of latent features and texture, improving scene understanding and generalization. sshELF can reconstruct 360 degree scenes from six sparse input views and achieves competitive results on synthetic and real-world datasets. We find that sshELF faithfully reconstructs occluded regions, supports real-time rendering, and provides rich latent features for downstream applications. The code will be released.

arXiv:2502.11054공식 코드 · Papers with Code

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models

Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. However, existing methods often struggle to balance semantic coherence with attack effectiveness, resulting in either benign semantic drift or ineffective detection evasion. To address this challenge, we propose Reasoning-Augmented Conversation, a novel multi-turn jailbreak framework that reformulates harmful queries into benign reasoning tasks and leverages LLMs' strong reasoning capabilities to compromise safety alignment. Specifically, we introduce an attack state machine framework to systematically model problem translation and iterative reasoning, ensuring coherent query generation across multiple turns. Building on this framework, we design gain-guided exploration, self-play, and rejection feedback modules to preserve attack semantics, enhance effectiveness, and sustain reasoning-driven attack progression. Extensive experiments on multiple LLMs demonstrate that RACE achieves state-of-the-art attack effectiveness in complex conversational scenarios, with attack success rates (ASRs) increasing by up to 96%. Notably, our approach achieves ASRs of 82% and 92% against leading commercial models, OpenAI o1 and DeepSeek R1, underscoring its potency. We release our code at https://github.com/NY1024/RACE to facilitate further research in this critical domain.

arXiv:2504.00908공식 코드 · Papers with Code

DBF-UNet: A Two-Stage Framework for Carotid Artery Segmentation with Pseudo-Label Generation

Medical image analysis faces significant challenges due to limited annotation data, particularly in three-dimensional carotid artery segmentation tasks, where existing datasets exhibit spatially discontinuous slice annotations with only a small portion of expert-labeled slices in complete 3D volumetric data. To address this challenge, we propose a two-stage segmentation framework. First, we construct continuous vessel centerlines by interpolating between annotated slice centroids and propagate labels along these centerlines to generate interpolated annotations for unlabeled slices. The slices with expert annotations are used for fine-tuning SAM-Med2D, while the interpolated labels on unlabeled slices serve as prompts to guide segmentation during inference. In the second stage, we propose a novel Dense Bidirectional Feature Fusion UNet (DBF-UNet). This lightweight architecture achieves precise segmentation of complete 3D vascular structures. The network incorporates bidirectional feature fusion in the encoder and integrates multi-scale feature aggregation with dense connectivity for effective feature reuse. Experimental validation on public datasets demonstrates that our proposed method effectively addresses the sparse annotation challenge in carotid artery segmentation while achieving superior performance compared to existing approaches. The source code is available at https://github.com/Haoxuanli-Thu/DBF-UNet.

arXiv:2504.13500공식 코드 · Papers with Code

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning

In this paper, we introduce a new \emph{process prejudge} strategy in LLM reasoning to demonstrate that bootstrapping with process prejudge allows the LLM to adaptively anticipate the errors encountered when advancing the subsequent reasoning steps, similar to people sometimes pausing to think about what mistakes may occur and how to avoid them, rather than relying solely on trial and error. Specifically, we define a prejudge node in the rationale, which represents a reasoning step, with at least one step that follows the prejudge node that has no paths toward the correct answer. To synthesize the prejudge reasoning process, we present an automated reasoning framework with a dynamic tree-searching strategy. This framework requires only one LLM to perform answer judging, response critiquing, prejudge generation, and thought completion. Furthermore, we develop a two-phase training mechanism with supervised fine-tuning (SFT) and reinforcement learning (RL) to further enhance the reasoning capabilities of LLMs. Experimental results from competition-level complex reasoning demonstrate that our method can teach the model to prejudge before thinking and significantly enhance the reasoning ability of LLMs. Code and data is released at https://github.com/wjn1996/Prejudge-Before-Think.

arXiv:2503.03854

Vision-Language Models Struggle to Align Entities across Modalities

Cross-modal entity linking refers to the ability to align entities and their attributes across different modalities. While cross-modal entity linking is a fundamental skill needed for real-world applications such as multimodal code generation, fake news detection, or scene understanding, it has not been thoroughly studied in the literature. In this paper, we introduce a new task and benchmark to address this gap. Our benchmark, MATE, consists of 5.5k evaluation instances featuring visual scenes aligned with their textual representations. To evaluate cross-modal entity linking performance, we design a question-answering task that involves retrieving one attribute of an object in one modality based on a unique attribute of that object in another modality. We evaluate state-of-the-art Vision-Language Models (VLMs) and humans on this task, and find that VLMs struggle significantly compared to humans, particularly as the number of objects in the scene increases. Our analysis also shows that, while chain-of-thought prompting can improve VLM performance, models remain far from achieving human-level proficiency. These findings highlight the need for further research in cross-modal entity linking and show that MATE is a strong benchmark to support that progress.

arXiv:2506.01111공식 코드 · Papers with Code

FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion

High-quality, large-scale audio captioning is crucial for advancing audio understanding, yet current automated methods often generate captions that lack fine-grained detail and contextual accuracy, primarily due to their reliance on limited unimodal or superficial multimodal information. Drawing inspiration from human auditory perception, which adeptly integrates cross-modal cues and performs sophisticated auditory scene analysis, we introduce a novel two-stage automated pipeline. This pipeline first employs specialized pretrained models to extract diverse contextual cues (e.g., speech, music, general sounds, and visual information from associated video). A large language model (LLM) then synthesizes these rich, multimodal inputs to generate detailed and context-aware audio captions. Key contributions of this work include: (1) the proposed scalable method for fine-grained audio caption generation; (2) FusionAudio, a new large-scale dataset comprising 1.2 million such detailed captions, combined with 6 million QA pairs; and (3) enhanced audio models developed using FusionAudio, specifically a CLAP-based audio encoder with superior audio-text alignment and instruction following. This paper paves the way for more nuanced and accurate automated understanding of complex audio environments. Code and data can be found in https://github.com/satsuki2486441738/FusionAudio.

arXiv:2605.15284v2cs.LG

Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning

We introduce Tadpole, a novel foundation model for three-dimensional partial differential equations (PDEs) that addresses key challenges in transferability, scalability to high dimensionality, and multi-functionality. Tadpole is pre-trained as an autoencoder on synthetic 3D PDE data generated by an efficient online data-generation framework. This enables large-scale, diverse training without storage or I/O overhead, demonstrated by scaling to an equivalent of hundreds of terabytes of training data. By autoencoding single-channel spatial crops, Tadpole learns rich and transferable representations across heterogeneous physical systems with varying numbers of state variables and spatial resolutions. Although pre-trained solely as an autoencoder, Tadpole can be efficiently applied for multiple downstream tasks beyond reconstruction, including dynamics learning and generative modeling. For dynamics learning, we propose a novel parameter-efficient fine-tuning strategy that integrates low-rank adaptation, latent-space transformations, and reintroduced skip connections, achieving accurate temporal modeling with a minimal number of trainable parameters. Tadpole demonstrates strong fine-tuning performance across various downstream tasks, highlighting its versatility and effectiveness as a foundation model for 3D PDE learning. Source code and pre-trained weights of Tadpole are available at https://tum-pbs.github.io/tadpole/.

arXiv:2603.29475v3cs.LG

Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks

Survival analysis is crucial for many medical applications, but remains challenging for modern machine learning due to limited data, censoring, and the heterogeneity of tabular covariates. While the prior-fitted paradigm, which relies on pretraining models on large collections of synthetic datasets, has recently facilitated tabular foundation models for classification and regression, its suitability for time-to-event modeling remains unclear. We propose a flexible survival data generation framework that defines a rich survival prior with explicit control over covariates and time-event distributions. Building on this prior, we introduce Survival In-Context (SIC), a prior-fitted in-context learning model for survival analysis that is pretrained exclusively on synthetic data. SIC is trained to approximate Bayesian posterior predictive inference under the synthetic survival prior, enabling individualized survival prediction in a single forward pass, requiring no task-specific training or hyperparameter tuning. Across a broad evaluation on real-world survival datasets, SIC achieves competitive or superior performance compared to classical and deep survival models, particularly in small and medium-sized data regimes, highlighting the promise of a prior-fitted paradigm for survival analysis. The code and pretrained models are available at https://github.com/yayapa/sic

arXiv:2605.13414v2cs.AI

TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints

Deploying language models as autonomous agents requires more than per-task accuracy: when an agent faces a queue of problems under a finite token budget, it must decide which to attempt, in what order, and how much compute to commit to each, all before any execution feedback is available. This is the prospective form of metacognitive control studied for decades in human cognition, yet whether language models possess it remains largely untested. We introduce TRIAGE, an evaluation framework in which a model receives a task pool and a token budget calibrated to its own baseline cost, and commits to a single ordered plan that jointly encodes selection, sequencing, and per-problem allocation. Plans are scored against an oracle built from the measured solvability and token costs of the model, using triage efficiency normalized between random and oracle performance, together with normalized regret relative to the oracle. We evaluate frontier and open-source models, with and without reasoning enabled, across competition mathematics, graduate-level science, code generation, and expert multidisciplinary knowledge, and find that current language models exhibit substantial gaps in prospective metacognitive control, revealing a previously unmeasured capability dimension with direct implications for resource-efficient agent deployment.

arXiv:2606.13625v1cs.CV

롱테일 감시 시나리오에서의 차량 색상 인식 재고찰

Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios

차량 색상 인식은 감시 시스템에서 차량 식별을 위한 중요한 단서로, 특히 저해상도, 가림, 모션 블러, 불량 조명으로 인해 번호판을 판독하기 어려운 경우에 더욱 중요하다. 그러나 실세계의 차량 색상 분포는 심각하게 불균형하여, 전체 정확도만으로는 빈도가 낮지만 운용상 중요한 색상에 대한 성능을 평가하기에 충분하지 않다. 본 논문은 도전적인 실세계 감시 데이터셋인 UFPR-VeSV를 사용하여 심각한 클래스 불균형 하에서 차량 색상 인식에 대한 포괄적인 연구를 제시한다. 우리는 두 가지 기성 생성 전략, 즉 RunDiffusion/JuggernautXL을 이용한 텍스트 조건부 이미지 생성과 Gemini 2.0 Flash를 이용한 이미지 조건부 색상 편집을 통해 소수 클래스 합성 증강을 조사한다. 선별된 합성 데이터는 현대적인 시각적 표현, 손실 재가중, 학습률 스케줄링, 색상 안전 증강, 전경 인식 전처리, 앙상블 퓨전과 결합된다. 최고 성능 접근법은 마이크로 정확도 94.6%, 매크로 정확도 79.7%를 달성하여, 최근 문헌 대비 매크로 정확도를 8.2 퍼센트 포인트 향상시켰다. 수동 오류 분석을 통해 남아 있는 많은 실패 사례가 인간 주석자에게도 시각적으로 모호함을 추가로 보여주며, 비제약 감시 영상에서 색상 기반 차량 식별의 실용적 한계를 부각시킨다. 생성된 이미지와 소스 코드는 https://github.com/viniciusorru/vcr-synthetic 에서 공개적으로 이용 가능하다.

arXiv:2607.14159v1cs.AI

MemoHarness: 경험으로부터 학습하는 에이전트 하네스

MemoHarness: Agent Harnesses That Learn from Experience

에이전트 하네스는 컨텍스트, 도구, 오케스트레이션, 메모리, 디코딩, 출력 처리를 관리하여 기본 LLM을 실행 가능한 에이전트로 전환하는 외부 제어 층이다. 하네스 설계는 에이전트 행동에 큰 영향을 미치지만, 대부분의 자동 개선 방법은 프롬프트, 파이프라인, 워크플로와 같은 더 좁은 산출물을 최적화하며, 배포된 에이전트는 보통 모든 경우에 단일 전역 하네스를 재사용한다. 우리는 자체 실행으로부터 학습하는 적응형 하네스 최적화 프레임워크인 MemoHarness를 제안한다. MemoHarness는 하네스를 여섯 개의 편집 가능한 제어 차원으로 분해하고, 사례별 진단과 정제된 전역 패턴을 이중 층 경험 뱅크에 저장하며, 테스트 시 레이블, 피드백, 추가 검색 없이 검색된 경험을 사용하여 학습된 하네스를 각 테스트 사례에 적응시킨다. 셸 에이전트, 코드 생성, 분석적 추론 벤치마크에 걸친 평가에서 MemoHarness는 우리가 비교한 고정 하네스보다 향상되며, 보지 못한 테스트 스위트와 기본 모델에 대한 선택적 전이를 보여준다. 검색된 경험의 상당 부분이 캐시 가능할 때 추가 컨텍스트도 비용 경쟁력을 유지할 수 있다. 이 결과는 실행 경험이 단일 정적 구성보다 더 적응적인 에이전트 하네스를 구축하기 위한 실용적인 기반임을 뒷받침하며, 통계적 견고성과 구성 요소 귀속에 대한 더 넓은 주장은 향후 연구에 맡긴다.