PulseAugur
EN
LIVE 14:44:24

New framework CurateEvo enhances LLM agent post-training data curation · 2 sources tracked

By PulseAugur Editorial · [4 sources] ·

Researchers have developed CurateEvo, a novel framework for dynamically evolving data curation strategies to improve the post-training of large language model (LLM) agents. This failure-driven approach iteratively refines curation methods by analyzing failed trajectories, leading to more effective and efficient data preparation for fine-tuning and reinforcement learning. Experiments on benchmarks like ACEBench-Agent and tau^2-Bench demonstrate that CurateEvo consistently outperforms existing curation techniques, enhancing agent performance and reducing overhead. AI

IMPACT This research introduces a more efficient and effective method for preparing data for LLM agents, potentially improving their performance on complex, long-horizon tasks.

RANK_REASON The cluster contains two identical arXiv preprints detailing a new data curation framework for LLM agents.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

New framework CurateEvo enhances LLM agent post-training data curation · 2 sources tracked

COVERAGE [4]

  1. arXiv cs.CL TIER_1 English(EN) · Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu, Wanxiang Che ·

    CurateEvo: Data-Curation Evolving for Agentic Post-Training

    arXiv:2607.06140v1 Announce Type: new Abstract: Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preproce…

  2. arXiv cs.CL TIER_1 English(EN) · Wanxiang Che ·

    CurateEvo: Data-Curation Evolving for Agentic Post-Training

    Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    CurateEvo: Data-Curation Evolving for Agentic Post-Training

    Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation…

  4. arXiv cs.AI TIER_1 English(EN) · Junze Ye, Jiayi Cheng, Miao Lu, Michal Mankowski, Jose Blanchet, Mohsen Bayati ·

    A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training

    arXiv:2607.04574v1 Announce Type: cross Abstract: For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on. Pure behavioral cloning uses full teacher demonstrations, creating a mismatch b…

RELATED ENTITIES

RELATED TOPICS