Tag
The paper introduces CLEAT, a framework that co-trains a clarification-value controller with an LLM task policy using paired rollouts to estimate residual query value, enabling agents to ask useful clarifying questions that adapt as the policy improves, achieving top scores across four benchmarks with Qwen3-4B.
SynCo 提出了一种基于多智能体强化学习的数据合成协同训练框架，联合优化 Synthesizer 与 Reasoner 两个智能体，使训练数据分布随模型能力共同演化，并在八个数学推理基准上取得了最强的整体表现。
The paper identifies an off-policy asymmetry in on-policy distillation, where the teacher must supervise student-generated prefixes it was not trained on, and proposes SCOUT, a co-training framework that adapts the teacher via RL with verifiable rewards, consistently improving distillation across configurations, scales, and reasoning domains.
The paper introduces NowWAM, a future-target-free co-training formulation that denoises the current observation and predicts robot actions from the same visual stream, showing that a separate future visual target is not essential for adapting pretrained generative DiTs to robot control while achieving 87.7% on LIBERO-Plus with FLUX2-Klein and a 1.8x speedup.
This paper addresses the knowledge boundary problem in visual generation by introducing the SearchGen-20K benchmark and SearchGen-Corpus-1M, and proposes a teach-then-search co-training framework to handle evolving, long-tailed user requests beyond a generator's training data.
This paper introduces PaW, a co-training framework that adds auxiliary world modeling supervision to policy learning during on-policy RL rollouts, improving language agent training without additional computational overhead.
CoHyDE introduces an iterative co-training procedure for an LLM rewriter and a dense encoder to improve tool retrieval from large API catalogs. It outperforms single-component baselines, especially on vague queries, by training both components together using InfoNCE and DPO.
Researchers from Fordham University introduce Reciprocal Co-Training (RCT), a framework that couples LLMs and Random Forest classifiers via reinforcement learning, creating an iterative feedback loop where each model improves using signals from the other. Experiments on three medical datasets show consistent performance gains for both models, demonstrating a general mechanism for integrating incompatible model families.