paper-with-me

Papers

SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback

2026-01-26 · Fangyuan Xu, Rujun Han, Yanfei Chen, Zifeng Wang, I-Hung Hsu, Jun Yan, Vishy Tirumalashetty, Eunsol Choi, Tomas Pfister, Chen-Yu Lee arxiv

Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively expensive due to long and complex exploration trajectories. We propose an agentic pipeline that automatically generates high quality, difficulty-controlled deep search question-answer pairs for a given corpus and a target difficulty level. Our pipeline, SAGE, consists of a data generator which proposes QA pairs and a search agent which attempts to solve the generated question and provide execution feedback for the data generator. The two components interact over multiple rounds to iteratively refine the question-answer pairs until they satisfy the target difficulty level. Our intrinsic evaluation shows SAGE generates questions that require diverse reasoning strategies, while significantly increases the correctness and difficulty of the generated data. Our extrinsic evaluation demonstrates up to 23% relative performance gain on popular deep search benchmarks by training deep search agents with our synthetic data. Additional experiments show that agents trained on our data can adapt from fixed-corpus retrieval to Google Search at inference time, without further training.

📄 PDF Abstract BibTeX arXiv:2601.18202

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Agentic-R: Learning to Retrieve for Agentic Search

2026-01-17 · Wenhan Liu, Xinyu Ma, Yutao Zhu, Yuchen Li 외 arxiv

Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic …

Answer Generation

Geometric and Physical Quantities Improve E(3) Equivariant Message Passing

2021-10-06 · ICLR 2022 4 · Johannes Brandstetter, Rob Hesselink, Elise van der Pol, Erik J Bekkers 외

Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that ge…

Graph Property Prediction

Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration

2026-07-30 · Ting Gong, Michael Ruofan Zeng, Yong Yang arxiv

Large language models can contribute useful ideas to mathematical research, yet long-horizon proof attempts remain difficult to coordinate, evaluate, and reproduce. We present Albilich, an open-source agentic harness for…

Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation

2026-04-12 · Fangda Ye, Zhifei Xie, Yuxin Hu, Yihang Yin 외 arxiv

Recent agentic search frameworks enable deep research via iterative planning and retrieval, reducing hallucinations and enhancing factual grounding. However, they remain text-centric, overlooking the multimodal evidence …

multimodal generation

Localizing RL-Induced Tool Use to a Single Crosscoder Feature

2026-06-25 · Andrii Shportko, Shubham Bhokare, Ahmed Zeyad A Alzahrani, Bowen Cheng 외 arxiv

Fine-tuning through RL reshapes the internal representations of language models to enable agentic behaviors such as tool use, yet the mechanistic basis of these changes remains poorly understood. While RL substantially i…