arXiv Machine Learning
5d ago
Latent On-Policy Self-Distillation
arXiv:2608. 13040v1 Announce Type: new Abstract: Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI.
Latent On-Policy Self-Distillation
Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effective pathway by using a privileged self-teacher to provide dense supervision on the student's own trajectories; however, existing methods still rely heavily on designer-specified privileged artifacts (e.
Related stories
arXiv AI
Aug 11
Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents
arXiv:2608. 09555v1 Announce Type: new Abstract: External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks.
arXiv AI
Aug 6
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
arXiv:2608. 04794v1 Announce Type: new Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it.
arXiv Machine Learning
Jun 4
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
arXiv:2606. 04703v1 Announce Type: cross Abstract: Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs).
arXiv Machine Learning
Jul 31
Group-Reflective Self-Distillation for Agentic Reinforcement Learning
arXiv:2607. 28076v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents.
arXiv AI
Jun 30
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
arXiv:2606. 29502v1 Announce Type: new Abstract: Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another.
arXiv AI
Aug 11
SR-OPSD: Self-Referenced On-Policy Self-Distillation
arXiv:2608. 09745v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards.
arXiv AI
Jul 28
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
arXiv:2607. 24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforcement learning (RL) provides only sparse supervision.
arXiv AI
Aug 5
Agentic Reinforcement Learning with Self-Distilled Reward Shaping
arXiv:2608. 03223v1 Announce Type: cross Abstract: Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit.
arXiv AI
Jun 3
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
arXiv:2606. 03841v1 Announce Type: new Abstract: Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science.
arXiv AI
Aug 11
Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation
arXiv:2608. 08176v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-distillation.
arXiv AI
1d ago
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
arXiv:2608. 15071v1 Announce Type: new Abstract: Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.