Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Intra-agent speech permits zero-shot task acquisition
Chen Yan, Federico Carnevale, Petko Georgiev, Adam Santoro, Aurelia Guy, Alistair Muldal, Chia-Chun Hung, Josh S Abramson, Timothy P Lillicrap, Greg Wayne
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use semi-supervised captioning instead of supervised, on novel drum object with 585 labeled samples | captioning model · Drum captioning | true positive rate: 20\% -> 70\% | Improved |
| add unpaired images via semi-supervised methods | captioning model · Playhouse captioning | log probability, CIDEr, color-object accuracy: equivalent to 3$\times$ more labeled data | Improved |
| add caption loss and caption-matching loss to behavioral cloning without drum interaction data | agent · lift drum and ask color drum | normalized reward: approximately $70\%$ of the performance | Improved |
| reduce labeled drum captions from 585 to 150 (ablation) | agent · drum color QA and lift drum | normalized reward: 585 -> 150 captions | No clear effect |
Closest papers by meaning
- Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination (NeurIPS 2025 · similarity 0.88)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.88)
- ESCA: Contextualizing Embodied Agents via Scene-Graph Generation (NeurIPS 2025 · similarity 0.87)
- VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought (NeurIPS 2024 · similarity 0.87)
- BEAR: Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis (ICML 2026 · similarity 0.86)
- MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World (CVPR 2024 · similarity 0.86)
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.
