Skip to content
← Back to explorer

RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy

Zhenhang Yuan, Shenghai Yuan, Lihua Xie · Mar 18, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Stale

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 18, 2026, 3:26 PM

Stale

Extraction refreshed

Mar 18, 2026, 3:26 PM

Stale

Extraction source

Persisted extraction

Confidence unavailable

Abstract

LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse. We identify two structurally coupled failure modes: (P1) invalid action generation and (P2) state drift, each amplifying the other in a degenerative cycle. We present RPMS, a conflict-managed architecture that enforces action feasibility via structured rule retrieval, gates memory applicability via a lightweight belief state, and resolves conflicts between the two sources via rules-first arbitration. On ALFWorld (134 unseen tasks), RPMS achieves 59.7% single-trial success with Llama 3.1 8B (+23.9 pp over baseline) and 98.5% with Claude Sonnet 4.5 (+11.9 pp); of the 8B gain, rule retrieval alone contributes +14.9 pp (statistically significant), making it the dominant factor. A key finding is that episodic memory is conditionally useful: it harms performance on some task types when used without grounding, but becomes a stable net positive once filtered by current state and constrained by explicit action rules. Adapting RPMS to ScienceWorld with GPT-4 yields consistent gains across all ablation conditions (avg. score 54.0 vs. 44.9 for the ReAct baseline), providing transfer evidence that the core mechanisms hold across structurally distinct environments.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Structured extraction is still processing; current fields are metadata-first.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

Signal extraction is still processing. This page currently shows metadata-first guidance until structured protocol fields are ready.

Best use

Background context only

Use if you need

A provisional background reference while structured extraction finishes.

Main weakness

Structured extraction is still processing; current fields are metadata-first.

Trust level

Provisional

Eval-Fit Score

Unavailable

Eval-fit score is unavailable until extraction completes.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Provisional (processing)

Extraction confidence: Provisional

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

provisional

None explicit

Confidence: Provisional Source: Persisted extraction inferred

No explicit feedback protocol extracted.

Evidence snippet: LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.

Evaluation Modes

provisional

None explicit

Confidence: Provisional Source: Persisted extraction inferred

Validate eval design from full paper text.

Evidence snippet: LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.

Quality Controls

provisional

Not reported

Confidence: Provisional Source: Persisted extraction inferred

No explicit QC controls found.

Evidence snippet: LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.

Benchmarks / Datasets

provisional

Not extracted

Confidence: Provisional Source: Persisted extraction inferred

No benchmark anchors detected.

Evidence snippet: LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.

Reported Metrics

provisional

Not extracted

Confidence: Provisional Source: Persisted extraction inferred

No metric anchors detected.

Evidence snippet: LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.

Rater Population

provisional

Unknown

Confidence: Provisional Source: Persisted extraction inferred

Rater source not explicitly reported.

Evidence snippet: LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.

Human Data Lens

Structured extraction is still processing. Below are provisional signals inferred from abstract text only.

  • Potential human-data signal: No explicit human-data keywords detected.
  • Potential benchmark anchors: No benchmark names detected in abstract.
  • Abstract highlights: 3 key sentence(s) extracted below.

Evaluation Lens

Evaluation fields are currently inferred heuristically from abstract text.

  • Potential evaluation modes: No explicit eval keywords detected.
  • Potential metric signals: No metric keywords detected.
  • Confidence: Provisional (metadata-only fallback).

Research Brief

Deterministic synthesis

LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.

Generated Mar 18, 2026, 3:26 PM · Grounded in abstract + metadata only

Key Takeaways

  • LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse.
  • We identify two structurally coupled failure modes: (P1) invalid action generation and (P2) state drift, each amplifying the other in a degenerative cycle.
  • We present RPMS, a conflict-managed architecture that enforces action feasibility via structured rule retrieval, gates memory applicability via a lightweight belief state, and resolves conflicts between the two sources via rules-first arbitration.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

No related papers found for this item yet.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote