Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Egocentric Planning for Scalable Embodied Task Achievement
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace FILM's template-based policies with iterative egocentric planning | FILM-style ALFRED agent · ALFRED Test Unseen | SR: 27.8 -> 36.07 | Helped |
| use ground-truth segmentation (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 45.13 | Helped |
| use ground-truth depth (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 41.85 | Helped |
| use ground-truth language (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 52.29 | Helped |
| use ground-truth segmentation, depth, and language (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 58.33 | Helped |
| remove the initial observation phase (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 30.75 | Hurt |
| reduce initial observations to 200 (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 37.3 | Hurt |
| remove object-preference search strategy (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 32.89 | Hurt |
| remove replanning-based fault recovery (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 27.31 | Hurt |
| replace symbolic planning with blind breadth-first search (ablation) | EPA · ALFRED Valid Unseen | SR: 40.11 -> 3.47 | Hurt |
| reuse the existing world model and specify new goals without adding task templates | EPA · Five new ALFRED task types | SR: 82\% | Helped |
Closest papers by meaning
- ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making (NeurIPS 2026 · similarity 0.88)
- Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning (NeurIPS 2025 · similarity 0.88)
- PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks (ICLR 2025 · similarity 0.87)
- Embodied Task Planning via Graph-Informed Action Generation with Large Language Models (ICML 2026 · similarity 0.87)
- Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (NeurIPS 2026 · similarity 0.87)
- OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning (ICLR 2026 · similarity 0.87)
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.