REVIEW 7 cited by
RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Owing to recent advancements, Large Language Models (LLMs) can now be deployed as agents for increasingly complex decision-making applications in areas including robotics, gaming, and API integration. However, reflecting past experiences in current decision-making processes, an innate human behavior, continues to pose significant challenges. Addressing this, we propose Retrieval-Augmented Planning (RAP) framework, designed to dynamically leverage past experiences corresponding to the current situation and context, thereby enhancing agents' planning capabilities. RAP distinguishes itself by being versatile: it excels in both text-only and multimodal environments, making it suitable for a wide range of tasks. Empirical evaluations demonstrate RAP's effectiveness, where it achieves SOTA performance in textual scenarios and notably enhances multimodal LLM agents' performance for embodied tasks. These results highlight RAP's potential in advancing the functionality and applicability of LLM agents in complex, real-world applications.
Forward citations
Cited by 7 Pith papers
-
The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
Conflicting memory enters early and propagates with weak recovery, producing similar compliance rates across models but larger absolute damage for stronger agents.
-
Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
FARMA forges and self-amplifies an agent's reasoning history with evasive language to induce unsafe skips; SENTINEL's Reasoning Guard reduces ASR to 0% across tested agents and models.
-
When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents
GhostWriter poisons tool-using personal agents' long-term memory via untrusted emails/calendar invites (~98% injection, ~60% activation); AM-Sentry policies and retrieval screens sharply reduce success while preservin...
-
MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM Agents
MAFIA poisons RAG agent memory through probing and compact factual cloaks, reaching up to 90.7% attack success while evading low-FPR input audits.
-
Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
Modeling agent trajectories as action-centric probabilistic graphs lets a GNN warn LLM agents of likely step-level errors before execution, improving pass ratio ~14.7% across four benchmarks.
-
Object-Centric Environment Modeling for Agentic Tasks
Object-Centric Environment Modeling (OCM) builds an online executable object-and-procedure code model that improves average rank and cuts invalid actions on ScienceWorld, ALFWorld, and PlanCraft.
-
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
FCGraft synthesizes code policies for embodied agents by grafting KV caches from a library of validated functions, claiming 18.31% higher success rate and 2.3x faster synthesis than prompt-level caching.
Discussion (0). Continue with ORCID to comment.