{"arxiv_id":"2608.21292","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":35,"sentences":59,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":2,"sentences":2,"quotes":[{"arxiv_id":"2412.15115","title":"Qwen2.5 Technical Report","url":"/paper/2412.15115","section":"Implementation Details","sentence":"Following Skill0.5 [ref] , we adopt Qwen2.5-7B-Instruct [ref] as the backbone policy model for all experiments.","intent_p":0.99,"contests_p":null},{"arxiv_id":"2605.28424","title":"Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning","url":"/paper/2605.28424","section":"Implementation Details","sentence":"Following Skill0.5 [ref] , we adopt Qwen2.5-7B-Instruct [ref] as the backbone policy model for all experiments.","intent_p":0.99,"contests_p":null}]},{"kind":"data_used","label":"Uses data or values from","papers":2,"sentences":2,"quotes":[{"arxiv_id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","url":"/paper/1704.05179","section":"Datasets","sentence":"We evaluate AUSO on three long-horizon agentic benchmarks: ALFWorld [ref] , WebShop [ref] , and SearchQA [ref] .","intent_p":0.83,"contests_p":null},{"arxiv_id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","url":"/paper/2207.01206","section":"Datasets","sentence":"We evaluate AUSO on three long-horizon agentic benchmarks: ALFWorld [ref] , WebShop [ref] , and SearchQA [ref] .","intent_p":0.83,"contests_p":null}]},{"kind":"comparison","label":"Compares with","papers":10,"sentences":10,"quotes":[{"arxiv_id":"2605.06130","title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","url":"/paper/2605.06130","section":"Baselines","sentence":"(5) Skill-augmented RL methods: SkillRL [ref] , Skill1 [ref] , SKILL0 [ref] , LatentSkill [ref] , and Skill0.5 [ref] , which represent recent attempts to train agents with external skills, internalized skills, or hybrid skill utilization and internalization.","intent_p":0.82,"contests_p":null},{"arxiv_id":"2604.02268","title":"SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization","url":"/paper/2604.02268","section":"Baselines","sentence":"(5) Skill-augmented RL methods: SkillRL [ref] , Skill1 [ref] , SKILL0 [ref] , LatentSkill [ref] , and Skill0.5 [ref] , which represent recent attempts to train agents with external skills, internalized skills, or hybrid skill utilization and internalization.","intent_p":0.82,"contests_p":null},{"arxiv_id":"2606.06087","title":"LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents","url":"/paper/2606.06087","section":"Baselines","sentence":"(5) Skill-augmented RL methods: SkillRL [ref] , Skill1 [ref] , SKILL0 [ref] , LatentSkill [ref] , and Skill0.5 [ref] , which represent recent attempts to train agents with external skills, internalized skills, or hybrid skill utilization and internalization.","intent_p":0.82,"contests_p":null},{"arxiv_id":"2605.28424","title":"Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning","url":"/paper/2605.28424","section":"Baselines","sentence":"(5) Skill-augmented RL methods: SkillRL [ref] , Skill1 [ref] , SKILL0 [ref] , LatentSkill [ref] , and Skill0.5 [ref] , which represent recent attempts to train agents with external skills, internalized skills, or hybrid skill utilization and internalization.","intent_p":0.82,"contests_p":null},{"arxiv_id":"2602.08234","title":"SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning","url":"/paper/2602.08234","section":"Baselines","sentence":"(5) Skill-augmented RL methods: SkillRL [ref] , Skill1 [ref] , SKILL0 [ref] , LatentSkill [ref] , and Skill0.5 [ref] , which represent recent attempts to train agents with external skills, internalized skills, or hybrid skill utilization and internalization.","intent_p":0.82,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":11,"sentences":11,"quotes":[{"arxiv_id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","url":"/paper/2207.01206","section":"Introduction","sentence":"Such interaction-centric settings are central to modern information access and decision-making tasks, including web shopping, embodied household execution, and search-based question answering [ref] .","intent_p":0.81,"contests_p":null},{"arxiv_id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","url":"/paper/1704.05179","section":"Introduction","sentence":"Such interaction-centric settings are central to modern information access and decision-making tasks, including web shopping, embodied household execution, and search-based question answering [ref] .","intent_p":0.81,"contests_p":null},{"arxiv_id":"2510.20113","title":null,"url":"/paper/2510.20113","section":"Introduction","sentence":"Such interaction-centric settings are central to modern information access and decision-making tasks, including web shopping, embodied household execution, and search-based question answering [ref] .","intent_p":0.81,"contests_p":null},{"arxiv_id":"2606.06087","title":"LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents","url":"/paper/2606.06087","section":"Agent Skills","sentence":"SKILL0 trains agents to absorb skill knowledge and reduce dependence on explicit skill prompts at inference time [ref] , while LatentSkill and Skill-to-LoRA study parameter or latent-space forms of skill internalization [ref] .","intent_p":0.81,"contests_p":null},{"arxiv_id":"2606.16769","title":null,"url":"/paper/2606.16769","section":"Agent Skills","sentence":"SKILL0 trains agents to absorb skill knowledge and reduce dependence on explicit skill prompts at inference time [ref] , while LatentSkill and Skill-to-LoRA study parameter or latent-space forms of skill internalization [ref] .","intent_p":0.81,"contests_p":null}]}],"unlabelled_sentences":34},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2608.21292"}}