AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents

Huanzhi Mao, Chengkun Cao, Shuo Yuan, Joseph Gonzalez

NeurIPS 2026 · Multi-agent systems and games › LLM agents · approach: Software engineering agent benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Interactive Programmatic Tool Calling (I-PTC), extending programmatic tool calling to stateful execution so agents can reuse intermediate results across tool-use programs.

Problem

Existing programmatic tool calling (PTC) approaches are largely stateless, which limits reuse of intermediate results and interaction across steps in tool-augmented agents.

Approach

Extends programmatic tool calling with interactive, stateful execution so that code-expressed tool use (loops, batching, abstraction) can persist and reuse intermediate results; the abstract does not give further details.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use programmatic tool calling instead of traditional tool callingGPT 5.4 · PTC-Benchpass rate: 18.6% -> 71.5%Improved
make PTC stateful and interactive (I-PTC)GPT 5.4 · PTC-Benchpass rate: 71.5% -> 80.0%Improved
make PTC stateful and interactive (I-PTC)Claude Opus 4.7 · PTC-Benchpass rate: 84.2% -> 82.9%Hurt
make PTC stateful and interactive (I-PTC)Qwen 3.5-397B-A17B · PTC-Benchpass rate: 75.3% -> 71.8%Hurt
use I-PTC instead of PTCClaude Opus 4.7 · PTC-Benchraw tokens: 184K -> 85KImproved
add persistent cells to stateless execution (ablation)GPT 5.4 mini and Gemini 3.1 Flash-Lite · PTC-Benchpass rate: +0.6 to +5.7 pointsImproved
add on-demand tool inspection (ablation)I-PTC on GPT 5.4 mini · PTC-Benchpass rate / raw tokens: 61.3 -> 68.1; 129K -> 44KImproved
add self-evolving API documentation (ablation)I-PTC on GPT 5.4 mini · PTC-Benchpass rate: 61.3 -> 62.9No clear effect
add documentation to stateless PTC (ablation)PTC on GPT 5.4 mini · PTC-Benchpass rate: 59.1 -> 57.2Hurt
delay documentation updates (larger batch size) (ablation)self-evolving docs · PTC-Bench mainAPI errorsHurt
use I-PTC instead of PTC on multi-turnGPT 5.4 mini · PTC-Bench multi-turnpass rate: 69.0% -> 77.1%Improved
use I-PTC instead of PTC on error recoveryGPT 5.4 mini · PTC-Bench error-recoverypass rate: 61.3% -> 72.9%Improved

Experimental setup

Builds on: programmatic tool calling

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy