AI Paper Atlas

Research map / Large language models / Agents, code and math

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning

Duo Wu, Jinghe Wang, Yuan Meng, Yanning Zhang, Le Sun, Zhi Wang

ICCV 2025 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add context augmentation for cost-aware features (ablation)CATP-LLM · OpenCATP sequentialQoP: 0.246 -> 0.261Improved
add intermediate reward feedback at each action (ablation)CATP-LLM · OpenCATP sequentialQoP: 0.209 -> 0.261Improved
add adaptive masking of invalid tool/dependency tokens (ablation)CATP-LLM · OpenCATP sequentialvalid plans: 70.2% -> 100%Improved
use CATP-LLM (Llama2-7B) instead of GPT-based methodstool planning · OpenCATP sequentialQoP: +1.5%-40.6% QoP on averageImproved
use CATP-LLM instead of RLTF (final-only feedback)Llama2-7B fine-tuning · OpenCATP sequentialQoP: 0.181 -> 0.261Improved
use CATP-LLM instead of GPT and fine-tuning baselinesnon-sequential planning · OpenCATP non-sequentialQoP: 92.0%-375.4% higher QoP on averageImproved
use tool planning language with CATP-LLM for non-sequential plansLlama2-7B · OpenCATP non-sequentialvalid plans: GPT-3.5 invalid 41.7%, 75%, 66.7% vs 100% validImproved
scale backbone from smaller models to Llama2-7B (ablation)CATP-LLM · OpenCATP non-sequentialQoPImproved
RLTF vs CATP-LLM on task scoresequential planning · OpenCATP sequentialTask score: 0.715 (RLTF) vs 0.681Mixed

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