REVIEW 8 cited by
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
RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
read the original abstract
Large language models (LLMs) struggle to effectively utilize a growing number of external tools, such as those defined by the Model Context Protocol (MCP)\cite{IntroducingMCP}, due to prompt bloat and selection complexity. We introduce RAG-MCP, a Retrieval-Augmented Generation framework that overcomes this challenge by offloading tool discovery. RAG-MCP uses semantic retrieval to identify the most relevant MCP(s) for a given query from an external index before engaging the LLM. Only the selected tool descriptions are passed to the model, drastically reducing prompt size and simplifying decision-making. Experiments, including an MCP stress test, demonstrate RAG-MCP significantly cuts prompt tokens (e.g., by over 50%) and more than triples tool selection accuracy (43.13% vs 13.62% baseline) on benchmark tasks. RAG-MCP enables scalable and accurate tool integration for LLMs.
Forward citations
Cited by 8 Pith papers
-
Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
Constrained decoding derived from OpenAPI specifications eliminates hallucinated web API calls in LLM-generated code and substantially improves correctness across 24 models, while retrieval-augmented generation yields...
-
MCP Server Architecture Patterns for LLM-Integrated Applications
Catalogues five MCP server architectural patterns observed across fifteen servers, plus anti-patterns and quantitative measurements on tool handling and overhead.
-
ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents
CMTF is a causal filtering method that reduces tool exposure to one per step while matching baseline success rates and cutting token use by ~90% in 102-task benchmarks with 100 tools.
-
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
Bits-over-Random (BoR) is a chance-corrected metric for tool shortlist evaluation that enables query-adaptive depth selection via RL, matching fixed-list coverage with shorter lists on BFCL and ToolBench.
-
More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
Skill shadowing, not context overhead, is the dominant cause of performance degradation when LLM agent skill libraries expand.
-
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
ComplexMCP benchmark shows current LLM agents achieve at most 60% success on interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.
-
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
ComplexMCP benchmark shows top LLM agents achieve under 60% success on dynamic interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.
-
Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery
Routing F1 for under-specified requests drops 16-23pp as agent catalog scales to 110, but embedding shortlisting recovers 10-17pp on a 584-tool enterprise system.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.