Chapter 2 · 2026
A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
Taiyi Wang, Sian Gooding, Florian Hartmann
Abstract
LLM-based agents struggle with long-horizon planning due to losing track of goals and sparse rewards in RL fine-tuning. This paper proposes a subgoal-driven framework with an agent that leverages proprietary models for online planning through subgoal decomposition. It also introduces MiRA (Milestoning your Reinforcement Learning Enhanced Agent), an RL training framework using dense, milestone-based reward signals, significantly improving long-horizon capabilities.
Topics
LLM agentslong-horizon planningsubgoal decompositionreinforcement learningweb navigation
Relevance Scores
Long-Horizon Score85
Enterprise Score80
Completeness75
Paper Info
Year2026
Venue
Type
ChapterCh. 2
Authors3
Zone III Analysis
Related Papers
ReAct: Synergizing Reasoning and Acting in Language Mod…
2023 · Ch.1
Reflexion: Language Agents with Verbal Reinforcement Le…
2023 · Ch.1
Tree of Thoughts: Deliberate Problem Solving with Large…
2023 · Ch.1
Toolformer: Language Models Can Teach Themselves to Use…
2023 · Ch.1
View all Chapter 2 papers →