Programmatic Tool Calling
PulseAugur coverage of Programmatic Tool Calling — every cluster mentioning Programmatic Tool Calling across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
ProgAgent framework enhances LLM tool orchestration via programmatic training
Researchers have introduced ProgAgent, a new training framework designed to improve how large language models (LLMs) orchestrate tools for complex, long-horizon tasks. Unlike traditional Direct Tool Calling (DTC) method…
-
OpenAI's Programmatic Tool Calling enables AI agents to write custom code
OpenAI's Programmatic Tool Calling feature allows an AI agent to write code for data filtering. In testing, this capability reduced costs for repetitive tasks while increasing expenses for novel research topics. The too…
-
Salesforce unveils enterprise AI model Koa; Bash outperforms specialized tools for agents
Salesforce has developed an enterprise language model called Koa, built upon Nemotron-3-Super-120B and enhanced with reinforcement learning. This model is designed for agentic tool use, particularly in customer relation…
-
Programmatic tool calling outperforms JSON for LLMs, study finds
A new paper evaluates programmatic tool calling (PTC) against traditional JSON tool calling for large language models. The study found that PTC, which exposes tools as typed Python stubs for models to invoke, matches or…
-
OpenAI's GPT-5.6 cuts token use with new code-writing tool orchestration
OpenAI has released GPT-5.6, a new family of models including Sol, Terra, and Luna, which significantly improves efficiency by writing code to orchestrate tool calls instead of invoking them one by one. This change, obs…