Chapter 2 · 2026
Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents
Zehong Wang, Fang Wu, Hongru Wang
Abstract
LLM-based agents often fail to sustain coherent behavior over long planning horizons due to a mismatch between step-wise reasoning and long-horizon planning. This paper argues that locally optimal choices lead to myopic commitments. It introduces FLARE (Future-aware Lookahead with Reward Estimation) to enforce explicit lookahead and value propagation, consistently improving task performance and planning-level behavior across benchmarks.
Topics
LLM agentslong-horizon planningreasoningdecision makingfuture-aware planning
Relevance Scores
Long-Horizon Score85
Enterprise Score80
Completeness75
Paper Info
Year2026
Venue
Type
ChapterCh. 2
Authors3
Zone III Analysis
Frameworks
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 →