Related papers: Skill-SD: Skill-Conditioned Self-Distillation for …

On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, existing OPSD methods often yield limited gains on in-domain…

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods…

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

Real world deployment of multi agent reinforcement learning MARL systems is fundamentally constrained by limited compute memory and inference time. While expert policies achieve high performance they rely on costly decision cycles and large…

The generalization capability of deep neural networks has been substantially improved by applying a wide spectrum of regularization methods, e.g., restricting function space, injecting randomness during training, augmenting data, etc. In…

Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally deviates from the ideal on-policy objective. To address this…

On-policy distillation (OPD) trains student models under their own induced distribution while leveraging supervision from stronger teachers. We identify a failure mode of OPD: as training progresses, on-policy rollouts can undergo abrupt…

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher…

Large language models (LLMs) are increasingly adapted to proprietary and domain-specific corpora that contain sensitive information, creating a tension between formal privacy guarantees and efficient deployment through model compression.…

Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. This requires efficiently managing the stability-plasticity…

Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed across many actions. Existing methods rely on…

On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens…

On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly treating the privileged teacher target as equally reliable at…

While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…

Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data…

Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decomposing state-action sequences into reusable skills and…

This work introduces a novel knowledge distillation framework for classification tasks where information on existing subclasses is available and taken into consideration. In classification tasks with a small number of classes or binary…

Recent advancements in large language models (LLMs) have exhibited promising performance in solving sequential decision-making problems. By imitating few-shot examples provided in the prompts (i.e., in-context learning), an LLM agent can…