Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Collaborative Planning with Encoding of Users' High-Level Strategies
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 |
|---|---|---|---|
| add user high-level strategies encoded as soft preferences | LPRPG-P planner · Zenotravel Numerical | plan cost: 13.0% / p=0.027 | Helped |
| add user high-level strategies encoded as soft preferences | OPTIC planner · Zenotravel Temporal | plan cost: 806 -> 656 (11.5% / p=0.031) | Helped |
| add user high-level strategies encoded as soft preferences | LPRPG-P planner · Zenotravel Propositional | plan cost: 53 -> 44.7 (1.7% / p=0.5) | No clear effect |
| add user high-level strategies encoded as soft preferences | LPRPG-P planner · Satellite Propositional | plan cost: -2.5% / p=0.25 | No clear effect |
| add user high-level strategies encoded as soft preferences | LPRPG-P planner · Satellite Numerical | plan cost: 15.9% / p=0.020 | Helped |
| add user high-level strategies encoded as soft preferences | OPTIC planner · Satellite Temporal | plan cost: 51 -> 40.3 (9.8% / p=0.027) | Helped |
| add user strategies as preferences to planner | automated planner · all six domain-complexity conditions | plan similarity to user plan (recall, relative sequencing): Zeno numerical recall 0.12 -> 0.24 | Helped |
| vary preference penalty weight lambda from 1% to 50% of estimated cost (ablation) | collaborative planner · user-strategy plans | plan cost | No clear effect |
Closest papers by meaning
- Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface (ICLR 2025 · similarity 0.87)
- TodoEvolve: Learning to Architect Agent Planning Systems (ICML 2026 · similarity 0.87)
- Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks (ICML 2025 · similarity 0.87)
- Agent-Oriented Planning in Multi-Agent Systems (ICLR 2025 · similarity 0.86)
- Strategic Planning: A Top-Down Approach to Option Generation (ICML 2025 · similarity 0.86)
- PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (ICML 2026 · 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.