{"arxiv_id":"2608.30429","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":14,"sentences":23,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":2,"sentences":2,"quotes":[{"arxiv_id":"2603.01145","title":null,"url":"/paper/2603.01145","section":"Experimental Setup","sentence":"Self-evolving Agents We evaluate SARGE on three representative self-evolving agents used as Target Agents, including AutoSkill [ref] , Voyager [ref] , and ExpeL [ref] .","intent_p":0.86,"contests_p":null},{"arxiv_id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","url":"/paper/2107.03374","section":"Evaluation Metrics","sentence":"To quantify the effectiveness of our red-teaming framework, we report a $pass@k$-style metric inspired by code generation evaluation [ref] . $k$ denotes the number of iterative attack loops performed by each Attack Agent.","intent_p":0.91,"contests_p":null}]},{"kind":"comparison","label":"Compares with","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2406.00083","title":"BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models","url":"/paper/2406.00083","section":"Experiment Design","sentence":"We also compare SARGE with representative attack methods, including jailbreak attacks [ref] , indirect prompt injection [ref] , memory poisoning [ref] , backdoor attacks [ref] , and RAG poisoning attacks [ref] , under identical evaluation settings.","intent_p":0.93,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":2,"sentences":5,"quotes":[{"arxiv_id":"2603.01145","title":null,"url":"/paper/2603.01145","section":"Introduction","sentence":"While earlier skill-based systems primarily relied on human-engineered skills or action patterns [ref] , recent studies propose self-evolving agents that autonomously generate and refine skills from interaction trajectories [ref] .","intent_p":0.9,"contests_p":null},{"arxiv_id":"2502.11090","title":null,"url":"/paper/2502.11090","section":"EvoSkillBench","sentence":"Existing agent attack benchmark datasets primarily focus on interaction-based attacks, such as harmful response generation, prompt injection, jailbreaking, and retrieval manipulation [ref] .","intent_p":0.9,"contests_p":null}]}],"unlabelled_sentences":15},"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/2608.30429"}}