{"arxiv_id":"2607.26722","incoming":{"papers":2,"sentences":2,"groups":[{"kind":"background","label":"Cites it as background","papers":2,"sentences":2,"quotes":[{"arxiv_id":"2608.20169","title":"Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection","url":"/paper/2608.20169","section":"Introduction","sentence":"Recently, automated harness optimization has begun to attract considerable attention, where a meta-level agent iteratively rewrites the harness code, evaluates the resulting candidates on a benchmark, and retains changes that improve performance [ref] .","intent_p":0.82,"contests_p":null},{"arxiv_id":"2608.23041","title":"AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces","url":"/paper/2608.23041","section":"Related Work","sentence":"Recent contemporaneous studies [These works appeared during the final stage of this work preparation or the subsequent peer-review period.] have further expanded automatic harness optimization through observability-driven evolution [ref] , diagnosis- and weakness-guided repair [ref] , Bayesian configuration search [ref] , historical-experience recalibration [ref] , self-supervised retrospective optimization [ref] , generalization-oriented constrained evolution [ref] , experience-driven test-time adaptation [ref] , and joint optimization of harnesses and model weights [ref] .","intent_p":0.85,"contests_p":null}]}],"unlabelled_sentences":0},"outgoing":{"papers":10,"sentences":16,"groups":[{"kind":"background","label":"Cites as background","papers":6,"sentences":9,"quotes":[{"arxiv_id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","url":"/paper/2510.04618","section":"Introduction","sentence":"Existing harness self-evolution methods, such as Meta-harness [ref] , AHE [ref] , and ACE [ref] , typically follow a history-driven paradigm.","intent_p":0.9,"contests_p":null},{"arxiv_id":"2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","url":"/paper/2603.28052","section":"Introduction","sentence":"Existing harness self-evolution methods, such as Meta-harness [ref] , AHE [ref] , and ACE [ref] , typically follow a history-driven paradigm.","intent_p":0.9,"contests_p":null},{"arxiv_id":"2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","url":"/paper/2604.25850","section":"Introduction","sentence":"Existing harness self-evolution methods, such as Meta-harness [ref] , AHE [ref] , and ACE [ref] , typically follow a history-driven paradigm.","intent_p":0.9,"contests_p":null},{"arxiv_id":"2603.03329","title":null,"url":"/paper/2603.03329","section":"Related Work","sentence":"AutoHarness synthesizes task-specific constraint code from environmental feedback [ref] .","intent_p":0.84,"contests_p":null},{"arxiv_id":"2606.09498","title":"Self-Harness: Harnesses That Improve Themselves","url":"/paper/2606.09498","section":"Related Work","sentence":"Self-Harness examines how harness modifications should be adapted to differing requirements of foundation models [ref] .","intent_p":0.88,"contests_p":null}]}],"unlabelled_sentences":7},"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/2607.26722"}}