AI Paper Atlas

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

CoPE: A Framework for Optimizing Coordination between Planning and Execution in LLM-based Agents

Huanxi Liu, Kun Hu, Qiang Wang, Yuanzhao Zhai, Feng Dawei, Bo Ding, Huaimin Wang

ICML 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent decision making

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 CoPE, a framework for fine-tuning LLM agents that coordinates long-term planning with multi-step execution to avoid impractical plans and plan-deviated trajectories.

Problem

Fine-tuning LLMs as autonomous agents on domain-specific data overlooks the coordination between long-term planning and multi-step execution, causing impractical plans and plan-deviated trajectories to propagate.

Approach

A framework that explicitly optimizes the coordination between planning and execution during agent fine-tuning, rather than treating them independently; details beyond the abstract are not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add coordination weighting to planning DPO (ablation)CoPE planning agent · AlfWorld Seen / ScienceWorld Seenaverage reward: 84.47 -> 88.00 and 61.22 -> 64.67Improved
use coordination label instead of reward-based weighting (ablation)CoPE planning agent · AlfWorld Seen / ScienceWorld Seenaverage reward: 82.60 -> 88.00 and 58.14 -> 64.67Improved
use coordination-weighted DPO instead of IPO-style loss (ablation)CoPE planning agent · AlfWorld Seen / ScienceWorld Seenaverage reward: 80.93 -> 88.00 and 58.28 -> 64.67Improved
add SFT loss to execution KTO (ablation)CoPE execution agent · AlfWorld Seen / ScienceWorld Seenaverage reward: 81.81 -> 88.00 and 51.63 -> 64.67Improved
add execution action pruning (ablation)CoPE execution agent · AlfWorld Seen / ScienceWorld Seenaverage reward: 76.65 -> 88.00 and 55.20 -> 64.67Improved
use coordination-label SFT weight instead of constant weight (ablation)CoPE execution agent · AlfWorld Seen / ScienceWorld Seenaverage reward: 72.49 -> 88.00 and 45.11 -> 64.67Improved
add replanning in MCTS node expansion (ablation)CoPE data collection · AlfWorldretention rate: 53.69% -> 57.43%Improved
add replanning in MCTS node expansion (ablation)CoPE data collection · AlfWorldSelf-BLEU of plans (lower more diverse): 0.48 -> 0.25Improved
add coordination modeling to preference optimization over iterations (ablation)CoPE · AlfWorld/ScienceWorld Seenaverage rewardImproved
use coordination-aware data instead of task-reward filteringCoPE vs RFT · ScienceWorldinvalid action rate: 10.78% -> 2.67%Improved
raise trajectory filter threshold beyond optimum (ablation)CoPE · AlfWorldaverage reward: peak at 0.8 then declinesHurt
train baselines on same data as CoPERFT/ETO/MPO/AGENTEVOL · AlfWorld Seenaverage reward: CoPE 88.00 vs AGENTEVOL 82.74No clear effect

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