cs.AINov 19, 2026

Seer: Guiding Small Deep-Research Agents with Shared Decision Models

Authors: Yuhao Zhou, Yang Zhou, Yuanxi Li, Jindi Lv, Dan Si, Qing Ye, Jiancheng Lv

Organizations: Sichuan University · University of Illinois at Urbana-Champaign · Lenovo Group Limited

Abstract

Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal. However, privacy and local control motivate running agents on users' devices, where limited memory and compute favor smaller models and complicate on-device training. Yet inference-time guidance faces three obstacles: exploring alternatives through real execution adds tool calls, prompted self-evaluation is bounded by the agent's judgment, and model-specific guidance risks repeated adaptation costs. We introduce Seer, an inference-time framework providing local guidance that separates the agent's action proposal from learned consequence prediction and value estimation. From a shared corpus of real research trajectories, we train two models: a tool-response simulator on observed call--response pairs and a value estimator on histories labeled with discounted terminal correctness. The simulator and estimator are trained offline and reused across agents without further training. Moreover, Seer executes only the selected action and adds only real tool responses to the committed history, avoiding tool calls on discarded candidates at additional inference cost. Across multiple deep-research benchmarks, Seer substantially improves agent performance for different language models. For instance, GAIA accuracy rises from 13.6% to 41.7% for Qwen3.5-4B and from 22.3% to 50.5% for Qwen3.5-9B. Furthermore, our analyses suggest that broader candidate coverage can compensate for imperfect simulation, while prediction and scoring errors limit the benefits of wider imagined search. These findings highlight the potential of reusable models for prediction and evaluation to strengthen small research agents through extra local computation without the real execution of the discarded candidates.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. VeriTrace: Evolving Mental Models for Deep Research Agents

    May 25, 2026Haolang Zhao, Yunbo Long, Lukas Beckenbauer +1Cognitive ModelingDeep Research Agents

  2. Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents

    Sep 1, 2026Ruochen Zhou, Zhengyu Chen, Luan Zhang +3Inference-Time SearchDeep Research Agents

  3. DeepResearch Agent System

    Jul 30, 2026Yong Huang, Yulu Huang, for the team CollaborationDeep Research AgentsLLM Inference Acceleration