arXiv Computation and Language
SearchJev: A Calibrated System-1 Model for Search Agents
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Oct 27
SearchHorizonBench: A Benchmark for Search Value in AI Agents
SearchHorizonBench is a new benchmark that evaluates how AI agents decide whether the cost of an additional search is justified by its expected benefit. It provides 45,632 executions on 3,168 questions, using paired continuations and repeated runs to separate true search gain from generation noise. The dataset shows that historical calibration can reduce Brier error by 16.2% and that free‑selection observations offer a 2.49‑point utility advantage over a constant action, highlighting the importance of accurate search‑value estimation.
arXiv Computation and Language
Sep 2
AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
AdaSearch introduces a two‑stage reinforcement learning framework that separates problem solving from the decision to search in large language models. By using an F1‑based decision metric, it explicitly evaluates when external search is needed, reducing unnecessary search calls while maintaining high question‑answering performance. Experiments show that AdaSearch improves search‑decision quality with only a minor impact on accuracy compared to always‑search strategies.
arXiv AI
3d ago
Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels
The paper introduces ZEST-Search, a zero-label framework that trains search agents by co-evolving task generation and solver learning. It constructs validated search tasks online from unlabeled questions, using a heterogeneous proposer to adapt task difficulty to the solver’s evolving capabilities. The approach rewards the proposer for intermediate difficulty and the solver for tool-aware performance, leading to improved search efficiency and accuracy across multiple question‑answering benchmarks.
arXiv AI
Oct 15
Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents
arXiv:2604.18235v3 Announce Type: replace-cross Abstract: Search agents achieve strong question-answering performance through multi-turn interactions with search engines, with Group Relative Policy O...
arXiv Computation and Language
Sep 1
Small Language Models as Judges for Rubric-Based Reinforcement Learning
arXiv:2608.30005v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific c...
arXiv Computation and Language
1d ago
EDU-Jev Training System-One Decision Models for Education
arXiv:2610.41079v1 Announce Type: new Abstract: Many automated decisions in education involve choosing from a fixed set of options: assigning a rubric score, checking whether an answer meets a markin...