EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

• URL: http://arxiv.org/abs/2606.11182v1
• Date: Tue, 09 Jun 2026 17:57:16 GMT
• Title: EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents
• Abstract summary: EEVEE is the first multi-dataset test-time prompt learning framework for LLM agents.<n>It enables test-time prompt learning under real-world task streams.<n>EEVEE improves average multi-benchmark scores by 10.38 and 24.32 points over Qwen3-4B-Instruct and DeepSeek-V3.2.
• Score: 64.96332056338923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose EEVEE, the first multi-dataset test-time prompt learning framework for LLM agents, enabling test-time prompt learning under real-world task streams. Existing methods are largely designed for single-dataset settings, while real-world applications require models to handle heterogeneous input streams drawn from multiple datasets, domains, and task distributions, limiting their practical applicability. To mitigate cross-dataset interference, EEVEE introduces a router that partitions incoming inputs into task clusters and assigns them to suitable prompt configurations. This design is optimized via a router-prompt co-evolution strategy, which employs interleaved router and prompt learning phases to address their mutual dependency. Experiments across multiple datasets demonstrate that the framework improves robustness under heterogeneous data streams while maintaining single-benchmark learning capability and efficiency. Specifically, EEVEE improves average multi-benchmark scores by 10.38 and 24.32 points over Qwen3-4B-Instruct and DeepSeek-V3.2, surpassing SOTA methods GEPA and ACE by up to 37.2% and 48.2%.

Related papers

• COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm [59.26203051651017]
  C-TAO is the first continuously annotated training set for Open-Vocabulary Multi-Object Tracking (OVMOT)<n>For the framework bottleneck, we propose COVTrack++, a synergistic framework that achieves a bidirectional reciprocal mechanism between detection and association through three modules.<n>Experiments on TAO demonstrate state-of-the-art performance, with novel TETA reaching 35.4% and 30.5% on validation and test sets, improving novel AssocA by 4.8% and novel LocA by 5.8% over previous methods.
  arXiv  Detail & Related papers  (2026-03-25T07:20:27Z)
• Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification [0.4925906256430175]
  LLM-guided neural architecture search (NAS) can automate this exploration, but most assume cloud execution or access to data-derived artifacts that cannot be exposed.<n>We present a novel data-local, LLM-guided search framework that handles candidate pipelines remotely while executing all training and evaluation locally under a fixed protocol.<n>Our framework targets multiclass, multimodal learning via one-vs-rest binary experts per class and modality, a lightweight fusion, and joint search over expert architectures and modality-specific preprocessing.
  arXiv  Detail & Related papers  (2026-03-16T21:46:05Z)
• Relatron: Automating Relational Machine Learning over Relational Databases [50.94254514286021]
  We present a study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks.<n>Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and accuracy is an unreliable guide for choice architecture.
  arXiv  Detail & Related papers  (2026-02-26T02:45:22Z)
• CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory [19.64051996386645]
  CREAM is a self-supervised framework for memory-based continual retrieval.<n>It adapts to both seen and unseen topics in an unsupervised setting.<n> Experiments on two benchmark datasets demonstrate that CREAM exhibits superior adaptability and retrieval accuracy.
  arXiv  Detail & Related papers  (2026-01-06T04:47:49Z)
• OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value [74.80873109856563]
  OpenDataArena (ODA) is a holistic and open platform designed to benchmark the intrinsic value of post-training data.<n>ODA establishes a comprehensive ecosystem comprising four key pillars: (i) a unified training-evaluation pipeline that ensures fair, open comparisons across diverse models; (ii) a multi-dimensional scoring framework that profiles data quality along tens of distinct axes; and (iii) an interactive data lineage explorer to visualize dataset genealogy and dissect component sources.
  arXiv  Detail & Related papers  (2025-12-16T03:33:24Z)
• Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning [53.527506374566485]
  We propose a novel Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning cluster framework, namely AR-DBSCAN.<n>We show that AR-DBSCAN not only improves clustering accuracy by up to 144.1% and 175.3% in the NMI and ARI metrics, respectively, but also is capable of robustly finding dominant parameters.
  arXiv  Detail & Related papers  (2025-05-07T11:37:23Z)
• PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning [13.564676246832544]
  We introduce PLANRL, a framework that chooses when the robot should use classical motion planning and when it should learn a policy. PLANRL switches between two modes of operation: reaching a waypoint using classical techniques when away from the objects and fine-grained manipulation control when about to interact with objects. We evaluate our approach across multiple challenging simulation environments and real-world tasks, demonstrating superior performance in terms of adaptability, efficiency, and generalization compared to existing methods.
  arXiv  Detail & Related papers  (2024-08-07T19:30:08Z)
• NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research [96.53307645791179]
  We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
  arXiv  Detail & Related papers  (2022-11-15T18:57:46Z)
• Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning [16.457778420360537]
  We propose a self-supervised learning solution for human activity recognition with smartphone accelerometer data. We develop a model that learns strong representations from accelerometer signals, while reducing the model's reliance on class labels. We evaluate the performance of the proposed solution on three datasets, namely MotionSense, HAPT, and HHAR.
  arXiv  Detail & Related papers  (2022-08-26T22:47:18Z)

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.