{"ID":2831095,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.08366","arxiv_id":"2512.08366","title":"Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making","abstract":"Large language model (LLM) agents often rely on external demonstrations or retrieval-augmented planning, leading to brittleness, poor generalization, and high computational overhead. Inspired by human problem-solving, we propose DuSAR (Dual-Strategy Agent with Reflecting) -- a demonstration-free framework that enables a single frozen LLM to perform co-adaptive reasoning via two complementary strategies: a high-level holistic plan and a context-grounded local policy. These strategies interact through a lightweight reflection mechanism, where the agent continuously assesses progress via a Strategy Fitness Score and dynamically revises its global plan when stuck or refines it upon meaningful advancement, mimicking human metacognitive behavior. On both simulated household (ALFWorld) and real-world web (Mind2Web) environments, DuSAR achieves state-of-the-art performance using only open-source LLMs, substantially outperforming all prior methods without any demonstrations or fine-tuning. Remarkably, it also reduces per-step token consumption by a large margin while maintaining strong task success. Ablation studies confirm the necessity of dual-strategy coordination. Moreover, optional integration of expert demonstrations further boosts performance, highlighting DuSAR's flexibility and compatibility with external knowledge.","short_abstract":"Large language model (LLM) agents often rely on external demonstrations or retrieval-augmented planning, leading to brittleness, poor generalization, and high computational overhead. Inspired by human problem-solving, we propose DuSAR (Dual-Strategy Agent with Reflecting) -- a demonstration-free framework that enables...","url_abs":"https://arxiv.org/abs/2512.08366","url_pdf":"https://arxiv.org/pdf/2512.08366v2","authors":"[\"Wentao Zhang\",\"Qunbo Wang\",\"BoXuan Zhao\",\"Tao Zhang\",\"Junsheng Wu\",\"Hongping Gan\",\"Ling Dai\",\"Shizhuang Deng\",\"Shuntong Sun\",\"Yang Liu\"]","published":"2025-12-09T08:44:59Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}