Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Information Shaping for Enhanced Goal Recognition of Partially-Informed Agents
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 CG-Pruning to BFS over sensor extensions (ablation) | information shaping search (FD) · WUMPUS-KEY | fraction completed: 0.13 -> 0.26 | Helped |
| add CG-Pruning to BFS over sensor extensions (ablation) | information shaping search (FD) · LOGISTICS-I | fraction completed: 0.4 -> 0.7 | Helped |
| add CG-Pruning (ablation) | information shaping search (FF) · LOGISTICS-I | fraction completed: 0.43 -> 0.92 | Helped |
| add CG-Pruning (ablation) | information shaping search (FD) · UNIX | average time (s): 179.6 -> 49.2 | Helped |
| add CG-Pruning (ablation) | information shaping search (FD) · WUMPUS | average time (s): 1184.32 -> 854.62 | Helped |
| add CG-Pruning (ablation) | information shaping search (FF) · TRAIL | average time (s): 70.65 -> 107.66 | Hurt |
| add CG-Pruning (ablation) | information shaping search (FF) · COLOR-BALLS | average time (s): 29.32 -> 55.23 | Hurt |
| add CG-Pruning (ablation) | information shaping search · all domains | WCD reduction | No clear effect |
| apply information shaping (sensor extensions) | goal recognition design with partially informed actor · LOGISTICS-I (FD) | WCD reduction: 3.91 | Helped |
| reveal more information to actor (non-monotonic) | GRD-APK · Wumpus example | WCD: 0 -> 4 | Mixed |
Closest papers by meaning
- Active Goal Recognition (AAAI 2020 · similarity 0.88)
- An LP-Based Approach for Goal Recognition as Planning (AAAI 2021 · similarity 0.87)
- A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals (ICLR 2025 · similarity 0.84)
- GoalLadder: Incremental Goal Discovery with Vision-Language Models (NeurIPS 2025 · similarity 0.84)
- InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents (ICLR 2026 · similarity 0.83)
- Generalized Intention Modeling in Multi-Agent Reinforcement Learning (NeurIPS 2026 · similarity 0.83)
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.