AI Paper Atlas

Research map / Large language models / Agents, code and math

An Interactive Paradigm for Deep Research

Lin Ai, Victor Bursztyn, Xiang Chen, Julia Hirschberg, Saayan Mitra

ICML 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use STEER interactive pausing and live persona instead of GPT-Researcher with full personaSTEER · Persona-query benchmarkAlignment: 79.48 -> 85.70Improved
add persona information to the baseline (query only to full persona)GPT-Researcher · Persona-query benchmarkAlignment: 66.63 -> 79.48Improved
add diversity-aware exploration (MMR) (ablation)STEER · Persona-query benchmarkFocus: 84.29 -> 87.79Improved
add Explore bonus (ablation)STEER · Persona-query benchmarkFocus: 85.17 -> 87.79Improved
add Explore bonus (ablation)STEER · Persona-query benchmarkAlignment: 84.98 -> 85.82No clear effect
add InfoGain utility (ablation)STEER · Persona-query benchmarkAlignment: 82.81 -> 85.82Improved
add InfoGain utility (ablation)STEER · Persona-query benchmarkDepth: 90.41 -> 90.27No clear effect
use cost-benefit pause rule with base cost C0 >= 0.4 instead of LLM PauseAgentSTEER · Persona-query benchmarknumber of pauses: PauseAgent exceeds Tol=3; STEER averages fewer than 3Improved
raise base pause cost C0STEER · Persona-query benchmarkAlignment per pause: local maxima around C0 = 0.7Mixed
use STEER instead of baselines in human pairwise comparisonSTEER · User study (20 query-persona pairs)Coverage (0-2): 0.828 -> 1.451Improved
use STEER instead of baselines in human pairwise comparisonSTEER · User study (20 query-persona pairs)Findability (0-2): 0.845 -> 1.534Improved
use STEER versus o4-mini-deep-research on depth and insightSTEER · Persona-query benchmarkInsight: 86.74 -> 83.04Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy