ProgAgent: Learning Tool Orchestration through Programmatic Training

Hao Li; Keqing He; Longtao Zheng; Junlong Li; Weihao Zeng; Qian Liu; Yuzhen Huang

cs.AIOct 10, 2026

ProgAgent: Learning Tool Orchestration through Programmatic Training

Authors: Hao Li, Keqing He, Longtao Zheng, Junlong Li, Weihao Zeng, Qian Liu, Yuzhen Huang

Organizations: Hong Kong University of Science and Technology · Beijing University of Posts and Telecommunications · Nanyang Technological University

Abstract

Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool Calling (DTC), where the model invokes tools sequentially, and tool responses accumulate in the model context, which can lead to context rot and orchestration breakdown. In contrast, Programmatic Tool Calling (PTC) invokes tools through executable code and stores intermediate results in runtime variables rather than appending them to the context. Prior work has explored PTC mainly as an inference-time optimization, but its benefits for agentic training remain unclear, and suitable verifiable training tasks are scarce. In this work, we introduce ProgAgent, a full PTC training stack, comprising a pipeline for synthesizing verifiable long-horizon tasks, a lightweight PTC runtime, and a two-stage training recipe. Using only 215 tasks instantiated at four environment scales, ProgAgent yields higher pass rates than the evaluated baselines of comparable size across four benchmarks. On LOCA-bench, ProgAgent-14B achieves a 30.7% pass rate at a 64k-token environment state, where these baselines score zero. Cross-harness experiments show that PTC-trained models outperform DTC-trained models under both evaluation interfaces, suggesting that the benefits of PTC training extend beyond the interface.

Figures & tables

Figure 1: Overview of ProgAgent. (a) Task synthesis. We construct verifiable tasks, scale their environment states from

v_{0}

v_{3}

while keeping instructions, task logic, and tool schemas fixed, and apply independent auditing and difficulty filtering. The scaling plot shows DeepSeek V4 Pro’s declining DTC pass@8 as environment size increases. (b) PTC runtime. A persistent IPython kernel executes tool-calling programs, retains intermediate results in variables across turns, and returns printed outputs to the agent. (c) Two-stage training. Cold-start SFT on teacher trajectories is followed by RL with binary rewards from Python task verifiers.

Figure 2: Direct tool calling (DTC) versus programmatic tool calling (PTC). DTC accumulates raw observations in the context, whereas PTC orchestrates tools via code and selectively prints outputs.

Method	TOUCAN	Simulator	EnvScaler	AWM	Agent-World	EnvFactory	ProgAgent
	( Xu et al., 2025 )	( Li et al., 2025b )	( Song et al., 2026 )	( Wang et al., 2026 )	( Dong et al., 2026 )	( Xu et al., 2026 )	(ours)
Tasks	1.53M traj.	135k traj.	11,572	3,315	2,000+	2,575	$215\times 4$

Table 1: Training-data scales across baselines (traj.: trajectories). Simulator aggregates synthesis settings; EnvScaler counts SFT + RL samples ( Xu et al., 2026 ) .

Panel of Table 2 — Table 2: Main results. Mean pass rates (%) on four benchmarks. Best and second-best scores within each 8B/14B comparison are bolded and underlined. Evaluation protocols and sources of reported scores are detailed in § 4.1 and Appendix C.4 .

Panel of Table 3 — Table 3: Training paradigms across benchmarks. Final pass rates (%) with the corresponding base model’s scores under the same harness shown in parentheses. Each trained model is evaluated under its training harness. The best score for each benchmark within each backbone is bolded.

Figure 3: Training paradigms on LOCA-bench. Each bar decomposes the final pass rate into the untrained backbone’s score and the gains from SFT and RL. Labels above the bars show rounded final pass rates; exact values are reported in Table 7 . Left: Results for the 8B and 14B backbones, averaged over four environment-state sizes. Right: Results for the 14B backbone at each environment-state size, showing PTC’s robustness as the environment grows.

Figure 4: RL training dynamics at 14B. Episode reward (left), tool-output tokens entering context (middle), and tool calls per episode (right) under DTC, Hybrid, and PTC.

Scale	Database Size (KB)	Workspace Files	pass@8
$v_{0}$	99	12.7	0.95
$v_{1}$	173	21.9	0.88
$v_{2}$	335	31.1	0.65
$v_{3}$	711	40.3	0.42

Table 4: Environment state and task difficulty. We present database size (KB), mean workspace file count, and DeepSeek V4 Pro’s DTC pass@8 across the four environment scales.

Model	Loops	Conditional execution	Error handling
8B	82.6	65.6	8.2
14B	82.1	64.0	9.5

Table 5: Programming structures used during RL. We present the percentage of generated code blocks using loops and conditional execution, and the percentage of executions using error handling.

Model	Eval	LOCA-bench			MCP-Atlas
Model	Eval	Base	DTC-trained	PTC-trained	Base	DTC-trained	PTC-trained
8B	DTC	0.3	4.0	6.0	7.6	19.0	30.6
	PTC	0.0	10.7	24.3	3.6	11.8	38.6
14B	DTC	0.3	9.0	13.9	12.4	29.7	41.6
	PTC	0.0	20.7	38.3	3.8	29.0	45.6

Table 6: Cross-harness evaluation on LOCA-bench and MCP-Atlas. Pass rates (%) under DTC and PTC evaluation for untrained backbones (Base) and models trained with the DTC or PTC SFT+RL recipe. LOCA-bench scores are averaged over four environment-state sizes.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 5: Distribution of 215 tasks across 23 domains.

Figure 6: Distribution of environment tool counts across the 215 tasks, excluding external harness tools. Each task is counted once.

Figure 7: Environment scaling under Hybrid and PTC. DeepSeek V4 Pro’s pass@8 on synthesized tasks at scales

v_{0}

–

v_{3}

; the DTC counterpart appears in Figure 1 .

Untrained base models
Model	Setting	8k		16k		32k		64k		Avg.
Model	Setting	SFT	+RL	SFT	+RL	SFT	+RL	SFT	+RL	SFT	+RL
8B	DTC	1.3		0.0		0.0		0.0		0.3
	Hybrid	1.3		0.0		0.0		0.0		0.3
	PTC	0.0		0.0		0.0		0.0		0.0
14B	DTC	1.3		0.0		0.0		0.0		0.3

Appendix

Table 7: Ablations on LOCA-bench. Pass rates (%) across four environment-state sizes. SFT and +RL denote checkpoints after supervised fine-tuning and subsequent reinforcement learning. For our trained models, Setting denotes the training paradigm; evaluation uses the same harness unless otherwise specified. Rows labeled “memory tool” use the DTC harness with the LOCA-bench memory tool. Values spanning the SFT and +RL columns report a single evaluated checkpoint.

Model	Environment	Tool calls	Tool-output tokens	Context limit (%)	DTC-like calls (%)
8B	Filesystem	50.5	21,086	16.7	6.21
	Postgres	68.3	22,404	36.9	18.00
	Notion	78.7	39,259	69.6	10.26
	Playwright	122.1	37,551	64.0	34.71
14B	Filesystem	34.9	15,925	8.8	10.10
	Postgres	58.0	22,200	8.3	14.70

Appendix

Table 8: Interaction costs of PTC on MCPMark. Tool calls and tool-output tokens are averaged per trajectory. Context limit reports the fraction of trajectories reaching the context limit. The “DTC-like calls” column reports the percentage of PTC calls containing a single explicit tool invocation without control flow, error handling, or selective printing; any printed tool return is reproduced in full without processing.

Figure 8: RL training dynamics at 8B. Episode reward (left), tool-output tokens entering context (middle), and tool calls per episode (right) under DTC, Hybrid, and PTC, with the same conventions as Figure 4 .

LLM Agent Orchestration

Large language model agent orchestration coordinates models, tools, and workflows to complete complex tasks reliably and efficiently.

See all 458 papers

The Bitter Lesson of Tool Calling
Aug 6, 2026Ishan Patel, Sahil Sen, Elias Lumer +1LLM Evaluation Tool-Augmented Language Model Agents
Commercial Technology and Innovation Office PricewaterhouseCoopers, U.S.A
HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents
Jun 11, 2026Yaxin Du, Yifan Zhou, Yujie Ge +7Tool-Augmented Language Model Agents LLM Agent Workflow Optimization
Shanghai Jiao Tong University · IQuest Research · Beijing University of Aeronautics and Astronautics
LLM-as-Code: Agentic Programming for Agent Harness
Jun 14, 2026Junjia Qi, Zichuan Fu, Jingtong Gao +4AI Agent Reliability LLM Agent Orchestration
City University of Hong Kong · Tencent Jarvis Lab

Aug 6, 2026J/K move · Enter open · S save

The Bitter Lesson of Tool Calling

Ishan Patel, Sahil Sen, Elias Lumer, Vamse Kumar Subbiah

Commercial Technology and Innovation Office PricewaterhouseCoopers, U.S.A

LLM Evaluation Tool-Augmented Language Model Agents LLM Tool Use

Open paper AskPDF arXiv

Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize naturally. However, a systematic evaluation of tools as code on an established benchmark across current and prior model generations under real-world task conditions has not been conducted. In this work, we empirically compare programmatic tool calling (PTC) to native JSON tool calling across 14 language models on BFCL v4. In the programmatic tool calling paradigm, tools are exposed as typed Python stubs that the model invokes through code, with execution and results handled in a single agent turn. Programmatic tool calling matches or exceeds native JSON tool calling in 11 of 14 models on BFCL v4, with the GPT-5.6 family achieving a 10.6% improvement over the JSON tool calling baseline. Further, it matches or outperforms baseline in 13 of 14 models under parallel fan-out, and holds stable under context rot conditions where baseline degrades 2.3% on average. Our results demonstrate that programmatic tool calling is a viable and robust alternative to JSON tool calling, with performance tracking model capability across release generations.

Abstract

LLM Agent Orchestration

Explore similar work

The Bitter Lesson of Tool Calling

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

LLM-as-Code: Agentic Programming for Agent Harness