PulseAugur
EN
LIVE 08:04:58

ProgAgent framework enhances LLM tool orchestration via programmatic training

By PulseAugur Editorial · [2 sources] ·

Researchers have introduced ProgAgent, a new training framework for large language models (LLMs) designed to improve tool orchestration for long-horizon tasks. Unlike Direct Tool Calling (DTC) which can suffer from context rot, ProgAgent utilizes Programmatic Tool Calling (PTC) to execute tools via code and store intermediate results in variables. This approach, trained on a synthesized set of verifiable tasks, demonstrated higher pass rates on benchmarks compared to DTC-trained models, even outperforming them significantly on the LOCA-bench with a 64k-token environment state. AI

IMPACT This research could lead to more robust and capable AI agents for complex, multi-step tasks.

RANK_REASON This is a research paper detailing a new framework and training methodology for LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

ProgAgent framework enhances LLM tool orchestration via programmatic training

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a research paper detailing a new framework and training methodology for LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
5 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Hao Li, Keqing He, Longtao Zheng, Junlong Li, Weihao Zeng, Qian Liu, Yuzhen Huang ·

    ProgAgent: Learning Tool Orchestration through Programmatic Training

    arXiv:2610.14774v1 Announce Type: new 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 acc…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    ProgAgent: Learning Tool Orchestration through Programmatic Training

    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 …

RELATED ENTITIES

RELATED TOPICS