paper-with-me

Papers

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

2026-06-01 · Zhongyu He, Yuanfan Li, Fei Huang, Tianyu Chen, Siyuan Chen, Xingyang Li, Meng Hsuan Yu, Xiangrong Liu, Leyi Wei, Lu Pan, Ke Zeng, Xunliang Cai arxiv

Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency. We propose Self-Internalizing Reinforcement learning with Intrinsic skills (SIRI), a three-phase framework that enables agents to discover, validate, and internalize skills without external skill generators or inference-time skill banks. SIRI first warms up the policy with GiGPO to acquire basic interaction ability and collect successful skill-free trajectories. It then performs self-skill mining, where the current policy summarizes compact skills from its own successful plain rollouts and validates them through paired skill-augmented and skill-free rollouts. Finally, SIRI distills only beneficial skill-guided action tokens into the plain policy using trajectory-level utility and action-level advantage. At inference, the agent runs with the original prompt only. On ALFWorld and WebShop with Qwen2.5-7B-Instruct, SIRI improves GiGPO from 0.908 to 0.930 on ALFWorld and from 0.728 to 0.813 on WebShop, outperforming prompt-based, RL-based, and memory-augmented baselines. Further analysis shows that our self-mining strategy can achieve performance comparable to distillation with closed-source large model. Our code is available at https://github.com/kirito618/SIRI.

📄 PDF Abstract BibTeX arXiv:2606.02355

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey

2020-12-17 · Cédric Colas, Tristan Karch, Olivier Sigaud, Pierre-Yves Oudeyer

Building autonomous machines that can explore open-ended environments, discover possible interactions and build repertoires of skills is a general objective of artificial intelligence. Developmental approaches argue that…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Towards Personalized Dialog Policies for Conversational Skill Discovery

2019-11-15 · Maryam Fazel-Zarandi, Sampat Biswas, Ryan Summers, Ahmed Elmalt 외

Many businesses and consumers are extending the capabilities of voice-based services such as Amazon Alexa, Google Home, Microsoft Cortana, and Apple Siri to create custom voice experiences (also known as skills). As the …

Reinforcement Learning

Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning

2026-05-11 · Han Zheng, Yining Ma, Karthick Gunasekaran, Bharathan Balaji 외 arxiv

In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics or auxiliary models, risking misalignmen…

Mathematical ReasoningCode Generation

PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

2026-07-23 · Yipeng Shi, Zhipeng Ma, Yue Wang, Qitai Tan 외 arxiv

In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimization. Existing skill-centric methods impro…

Reinforcement Learning

UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents

2026-02-05 · Han Xiao, Guozhi Wang, Hao Wang, Shilong Liu 외 arxiv

Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-hor…

Reinforcement Learning