Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Instructable Intelligent Personal Agent
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 |
|---|---|---|---|
| let users teach new commands by natural language instruction (with lexicon induction) | LIA · MTurk email tasks | time on main task: 39.4% time saved (12:08 of 30:28) | Helped |
| user programming background (higher acquaintance) | LIA · MTurk email tasks | commands gained from taught commands: correlation 0.1 | No clear effect |
| subjects with no programming knowledge using teaching | LIA · MTurk email tasks | commands gained: 43.3 average commands gained (6 subjects) | Helped |
| restrict to subjects who completed all tasks (more interaction time) | LIA · MTurk email tasks | unknown-command parse rate: 15.4% -> 9.9% | Helped |
Closest papers by meaning
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills (NeurIPS 2026 · similarity 0.86)
- Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments (ICLR 2025 · similarity 0.85)
- Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis (AAAI 2024 · similarity 0.85)
- Offline Training of Language Model Agents with Functions as Learnable Weights (ICML 2024 · similarity 0.85)
- Self-Challenging Language Model Agents (NeurIPS 2025 · similarity 0.85)
- AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning (NeurIPS 2024 · 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.