Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution

2026-08-07

AI Summary

This work addresses the limitations of existing large language model agents in solving complex software problems, which often stem from a decoupling between planning and memory mechanisms, leading to reliance on outdated information, repeated errors, and insufficient execution validation. To overcome these issues, the authors propose a bidirectionally coupled architecture integrating hierarchical planning with episodic memory: the current plan guides memory retrieval, while statistical summaries of past trajectories enable stall detection and trigger replanning. Crucially, reproducibility judgments are introduced as executable evidence to enhance verification reliability. This approach achieves the first dynamic synergy between planning and memory, yielding consistent performance gains across benchmarks—solving 25 additional cases on average (+5.0 percentage points) on SWE-bench Verified, and significantly reducing recurrent failures, empty-patch exits, and context exhaustion in Verified-500 and TerminalWorld.

Abstract

Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification. Success depends on both the base model's local reasoning and the agent's ability to maintain an evolving plan and remember observations across phases. Existing repository-level agents typically strengthen planning or memory in isolation, leaving long trajectories vulnerable to stale evidence, repeated failed edits, and verification inferred from the agent's own claims instead of execution evidence. We present PMCoder, an issue-resolution agent that couples a hierarchical phase planner with episodic memory. The coupling is bidirectional: the current plan phase conditions memory retrieval, while memory-derived trajectory statistics inform stuck detection and replanning. When available, issue-reproduction verdicts ground verification progress in execution evidence rather than self-reported completion. On SWE-bench Verified, PMCoder resolves an average of $25$ more cases ($+5.0$pp) than a harness-matched baseline, with gains persisting even where the reproduction gate never fires. Further Verified-500 evaluations show the same positive direction across Claude Haiku 4.5, DeepSeek-V4-Flash, and an OpenHands port, with at least $14$ additional resolved cases ($+2.8$pp). Separately, evaluation on TerminalWorld's official sample suggests that the plan-memory substrate transfers beyond issue reports. Ablation and trajectory analyses show where the gains come from: coupling planning and memory outperforms either component alone and reduces repeated failed actions, empty-patch exits, and context-window exhaustion.

Problem

• software issue resolution
• LLM agents
• episodic memory
• planning
• long-horizon reasoning

Innovation

• hierarchical planning
• episodic memory
• LLM agent
• software repair
• execution-grounded verification