COEVO is introduced, a framework that updates model parameters from on-policy experience while adapting contextual guidance according to the state of the evolving policy, and suggests that external context should be viewed not merely as a fixed interface to a large language model, but as an adaptive component of recursive self-improvement.
Abstract
Recursive self-improvement (RSI) seeks to move large language models beyond static training pipelines toward systems that can participate in improving their own future behavior. Existing approaches largely follow two directions: updating model parameters through online learning, or improving the external context through search, reflection, and prompt optimization. Although both mechanisms can support continued improvement, they are typically studied independently. This separation overlooks an important interaction: the context shapes the experience from which a model learns, while an evolving model may interpret and utilize the same context differently over time. We therefore formulate RSI as a problem of parameter--context co-evolution, where model parameters and the learning context adapt within a shared feedback loop. We introduce COEVO, a framework that updates model parameters from on-policy experience while adapting contextual guidance according to the state of the evolving policy. Policy entropy and prompt-conditioned attention are used as complementary signals to guide this adaptation. Experiments show that COEVO consistently improves task performance over fixed-context reinforcement learning and produces policies that are more robust to changes in system prompts. More broadly, our results suggest that external context should be viewed not merely as a fixed interface to a large language model, but as an adaptive component of recursive self-improvement.
Adapting general-purpose large language models to specific tasks requires substantial human effort in designing data and training strategies. Sustaining improvement is especially challenging because model updates change the error distribution, requiring strategies to be continually refined. We introduce ImproveAnyTask,...
Xing-Bo Yao, Xiao-Man Wang, Zheng-Wu Lei et al.· 2 citations
A-RSI monitors reward variation and accuracy in training logs to refresh a task pool to refresh a task pool when its learning signal declines, without consulting validation or test scores.
Yu Liu, You-Xing Li, Yue-Dong Tan et al.· 0 citations
A holistic framework based on learnable information gain, which measures how much novel, parameterizable information a round provides relative to the previous round, and proposes ATRI (Adaptive Training Regulation via Information-gain), which reweights samples within a round and halts training across rounds when inform...
Chen-Xu Wang, Chao-Zhuo Li, Xin-Ze Shi et al.· arXiv.org· 0 citations
This paper proposes TTSE (Two-Track Self-Evolution), a dual-track online self-evolution framework that separates evolving knowledge into FACT (environmental facts, whose reliability is continuously verified through interaction evidence) and TIP (task-conditioned implementation procedures), and broadly compatible with e...
This work proposed PLUME, a training-free method that constructs a global update representation, activates memory evidence to form a local parameter view, and adaptively integrates their predictions during decoding, which demonstrated its effectiveness in sequential evolution settings.
A bounded-history context-management framework that predicts the task-dependent downstream effect of removing historical interactions to guide history selection and determine a decision-dependent context budget is proposed.
Rui-Han A. Li, Shang-Tong Zhang, Rohan Chandra· 0 citations