{"ID":22952764,"CreatedAt":"2026-09-17T02:12:05.498442134Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.18909","arxiv_id":"2609.18909","title":"Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking","abstract":"Agent benchmarks are substantially more costly to evaluate than conventional LLM benchmarks. Benchmark compression is therefore a natural solution, yet existing methods primarily model redundancy in task--model final-score distributions, which is important in agentic evaluation. To address this limitation, we analyze large-scale trajectories and identify six complementary process signals that are systematically associated with final agent performance. To disentangle agent performance redundancy from a complete perspective, we propose DualViewEval, an agent benchmark compression method that jointly exploits outcome and process relations to learn an exact-size miniset and predict the full-benchmark scores. Across five agent benchmarks and five representative baselines, DualViewEval achieves the best results in all datasets. With only 20 tasks, it achieves $24\\times$--$40\\times$ compression on APEX-Agents and BFCL, reducing mean absolute error (MAE) by $14.5\\%$--$28.2\\%$ over the strongest competitors while improving Kendall's $τ$ by up to $7.2\\%$ relative to EssenceBench on SWE-bench Verified. The selected minisets further reveal capability differences among different agents, providing compact and diagnostic feedback for efficient agentic model development.","short_abstract":"Agent benchmarks are substantially more costly to evaluate than conventional LLM benchmarks. Benchmark compression is therefore a natural solution, yet existing methods primarily model redundancy in task--model final-score distributions, which is important in agentic evaluation. To address this limitation, we analyze l...","url_abs":"https://arxiv.org/abs/2609.18909","url_pdf":"https://arxiv.org/pdf/2609.18909v1","authors":"[\"Xinshuai Guo\",\"Junjie Wu\",\"Dolly Deng\",\"Yinghui Li\",\"Hai-Tao Zheng\",\"Suncong Zheng\",\"Maxm Pan\"]","published":"2026-09-16T16:49:50Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}