The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
cs.CL, cs.AI, cs.LG, cs.MA, cs.SE
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/tatsu-lab/stanford_alpaca
Project page: https://heelo.dev
Terminology
Sources
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Gorilla: Large Language Model Connected with Massive APIs
- MemGPT: Towards LLMs as Operating Systems
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- ToolACE: Winning the Points of LLM Function Calling
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Agent Workflow Memory
- TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks
- Automated Design of Agentic Systems
- AFlow: Automating Agentic Workflow Generation
- JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
- Large-scale Repository Engineering via Agent-Native Reusable Code Primitives
- Can the Library Speak? Self-Advertised Method Selection for Formal Proving
- From Knowledge Access to Source Learning: Developing Source-Specific Competence
- Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems
- Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
- ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data