Natural Language Interface for LLM Tool Calling
Use natural language as the interface for tool calling in LLMs.
Replace rigid API schema-based invocation with natural language as the interface for tool calling.
Each tool is wrapped with an LLM interface that handles schema resolution and execution internally. This enables natural inter-tool communication for nested and multi-turn tool calling.
Instead of specifying `tool_name(param1='value1', param2='value2')`, an LLM can interpret a request like 'Use the weather tool to find the forecast for London.'
Adopt a natural language interface for LLM tool calls. This approach abstracts away complex schemas, allowing LLMs to interact with tools more intuitively and enabling better multi-step execution.
Natural language interfaces simplify tool interaction for LLMs, making it easier to chain tools and manage complex, multi-turn tasks without explicit schema management.
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives ↗arXiv · arXiv cs.AI · Sep 1, 2026 · paraphrased
First seen on Subvolts Sep 1, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool PrimitivesAnthropic · arXiv cs.AI · Sep 1, 2026
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool PrimitivesGoogle · arXiv cs.AI · Sep 1, 2026
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool PrimitivesOpenAI · arXiv cs.AI · Sep 1, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- HeuristicFocus memory use on evidence, not just relevanceShift LLM memory use from finding relevant past info to building specific evidence sets for queries. · 30 min
- HeuristicUse latent uncertainty for agent escalation decisionsCompare weak agent's current hidden states to past successful and failed trajectories to measure uncertainty. · 30 min
- HeuristicAnticipatory Directed Curation for LLM WorkspacesProactively reorganize unstructured corpora before inference to efficiently serve diverse future queries. · 30 min
- HeuristicProgress-potential reward shaping for agent trainingConvert progress metrics into dense per-step rewards to improve agent training efficiency on long-horizon tasks. · 15 min
- HeuristicConsider engineering constraints beyond functional correctness for AI agentsAI coding agents must follow developer-defined constraints like scope, order, validation, tool use, and reporting, not just produce working code. · 5 min
- ChecklistSWE-Duel Agent Evaluation CriteriaCriteria for admitting a pull request and for a Blue agent to win in the SWE-Duel arena. · 5 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with in the sources.
- Where did this come from?
- arXiv (arXiv cs.AI). Subvolts collected, normalized and credited it; the link above opens the original.