Agents equipped with search tools have emerged as effective solutions for knowledge-intensive tasks. While Large Language Models (LLMs) exhibit strong reasoning capabilities, their high computational cost limits practical deployment for search agents. Consequently, recent work has focused on distilling agentic behaviors from LLMs into Small Language Models (SLMs). Through comprehensive evaluation on complex multi-hop reasoning tasks, we find that despite possessing less parametric knowledge, SLMs invoke search tools less frequently and are more prone to hallucinations. To address this issue, we propose \policy, a lightweight fine-tuning approach that explicitly trains SLMs to reliably retrieve and generate answers grounded in retrieved evidence. Compared to agent distillation from LLMs, our approach improves performance by 17.3 scores on Bamboogle and 15.3 scores on HotpotQA, achieving LLM-level results across benchmarks. Our further analysis reveals that adaptive search strategies in SLMs often degrade performance, highlighting the necessity of consistent search behavior for reliable reasoning.
Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles
Acting Less is Reasoning More! Teaching Model to Act Efficiently
The Chinese University of Hong Kong（香港中文大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴娜-香槟分校）；Princeton University（普林斯顿大学）；Sun Yat-sen University（中山大学）；Hong Kong University of Science and Technology（香港科学理工大学）
Combining Relational Algebra, SQL, Constraint Modelling, and Local Search
本文的目标是提供一个强大的约束建模和关系数据库管理系统之间的集成。为此，我们建议扩展标准的查询语言，如关系代数和SQL，通过添加约束建模功能。特别是，我们提出了两种语言，这是特别适合于组合问题的非确定性扩展。非确定性是通过猜测算子引入的，它声明一组关系具有任意扩展。这个新的运算符导致语言具有更高的表达能力，能够表达复杂性类NP中的所有问题。给出了使数据复杂度多项式化的一些语法限制。这两个扩展的有效性证明了通过几个例子。目前的实现，用Java编写的本地搜索技术，描述。逻辑程序设计理论与实践（Theory and Practice of Logic Programming，TPLP）
Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
The Chinese University of Hong Kong（香港中文大学）；LLM Department, Tencent（腾讯语言模型部门）；Mohamed bin Zayed University of Artificial Intelligence（马尔代夫人工智能大学）；McGill University（麦吉尔大学）；City University of Hong Kong（香港城市大学）；The University of Edinburgh（爱丁堡大学）
