AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Active Reasoning in an Open-World Environment

Manjie Xu, Guangyuan Jiang, Wei Liang, Chi Zhang, Yixin Zhu

NeurIPS 2023 · Large language models › Retrieval and knowledge · approach: Explanatory and multiple-choice QA benchmarks · 3 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 the Ideal explorer instead of the TRPO explorer (ablation)FrozenBiLM-DeBERTa · Active reasoning QA overallaccuracy (%): 65.3 -> 77.8Improved
use the Ideal explorer instead of the TRPO explorer (ablation)Flamingo-Mini · Active reasoning QA overallaccuracy (%): 66.3 -> 69.0Improved
use the Ideal explorer instead of the TRPO explorer (ablation)Vanilla-Trans · Active reasoning QA overallaccuracy (%): 28.8 -> 66.1Improved
use the Ideal explorer instead of the TRPO explorer (ablation)FrozenBiLM-BERT · Active reasoning QA overallaccuracy (%): 61.0 -> 74.0Improved
use the Ideal explorer instead of the TRPO explorer (ablation)FrozenBiLM-DeBERTa · Goal questionsaccuracy (%): 43.1 -> 71.8Improved
replace TRPO explorer with empty visual inputs (ablation)FrozenBiLM-BERT · Goal questionsaccuracy (%): 44.4 -> 25.5Hurt
replace TRPO explorer with empty visual inputs (ablation)Flamingo-Mini · Goal questionsaccuracy (%): 43.3 -> 22.9Hurt
use AFD (deductive simulation) instead of the standard setting (ablation)FrozenBiLM-BERT · Active reasoning QA overallaccuracy (%): 61.0 -> 66.0Improved
use AFD instead of the standard setting (ablation)FrozenBiLM-DeBERTa · Active reasoning QA overallaccuracy (%): 65.3 -> 65.4No clear effect
use AFD instead of the standard setting (ablation)Flamingo-Mini · Active reasoning QA overallaccuracy (%): 66.3 -> 66.1No clear effect
use AFD instead of the standard setting (ablation)FrozenBiLM-BERT · Survival questionsaccuracy (%): 54.4 -> 55.5Improved
use AFD instead of the standard setting (ablation)Vanilla-Trans · Active reasoning QA overallaccuracy (%): 28.8 -> 24.3Hurt

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