Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution
Ramya Ramakrishnan, Ece Kamar, Besmira Nushi, Debadeepta Dey, Julie Shah, Eric Horvitz
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 |
|---|---|---|---|
| add greedy feature selection to prune distractor and redundant features (ablation) | blind spot hand-off · Catcher and Driving | average reward | Improved |
| use learned blind spot models for hand-off instead of agent-only or human-only execution | blind spot hand-off · Catcher and Driving | average reward | Improved |
| increase amount of human demonstration data (ablation) | blind spot hand-off · Catcher and Driving | average reward | Improved |
| add prior estimation for agent/human blind spot proportions (ablation) | blind spot hand-off · Catcher | fraction of agent acting | Improved |
| increase human random suboptimality (ablation) | blind spot hand-off · Driving | average reward | Hurt |
| label non-activated mismatches as human blind spots so agent is preferred when both can act (ablation) | blind spot hand-off · Driving with noisy human | average reward | Improved |
Closest papers by meaning
- Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames (NeurIPS 2025 · similarity 0.87)
- Behavioral Exploration: Learning to Explore via In-Context Adaptation (ICML 2025 · similarity 0.85)
- A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search (NeurIPS 2025 · similarity 0.85)
- A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals (ICLR 2025 · similarity 0.85)
- Building a Foundational Guardrail for General Agentic Systems via Synthetic Data (ICLR 2026 · similarity 0.84)
- CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation (ICML 2026 · similarity 0.84)
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.
