Jiahe Geng writes about RSM-full, an online clustered-memory pipeline designed to optimize the quality-to-token trade-off for long-horizon LLM deployments with limited prompt budgets. By utilizing a cosine-gated max-member merge rule and atom-aware grouped context packing, the method achieves significant performance gains in compact-memory regimes compared to existing baselines like Online K-Means and A-MEM. The approach is particularly effective when maintaining an answer quality of 83% for Full-Context level tasks while utilizing only 32% of the total token cost within a 4k budget.
- RSM-full outperforms Streaming-Proto by +2.97 percentage points on the RealMem benchmark.
- The performance gain is primarily driven by the merge rule and grouped packing rather than just flat concatenation or simple clustering.
- The method reaches its optimal utility in the 2k to 5k prompt token range.
- RSM-full outperforms Streaming-Proto by +2.97 percentage points on the RealMem benchmark.
- The performance gain is primarily driven by the merge rule and grouped packing rather than just flat concatenation or simple clustering.
- The method reaches its optimal utility in the 2k to 5k prompt token range.
> Lessons from building a fast, reliable scientific agent with local open-weight models, vLLM, and long-context infrastructure
A new ETH Zurich study challenges the common practice of using `AGENTS.md` files with AI coding agents. LLM-generated context files decrease performance (3% lower success rate, +20% steps/costs).Human-written files offer small gains (4% success rate) but also increase costs. Researchers recommend omitting context files unless manually written with non-inferable details (tooling, build commands).They tested this using a new dataset, AGENTbench, with four agents.
mcp-cli is a lightweight CLI that enables dynamic discovery of MCP servers, reducing token consumption and making tool interactions more efficient for AI coding agents.
This blog post explains that Large Language Models (LLMs) don't need to understand the Model Context Protocol (MCP) to utilize tools. MCP standardizes tool calling, simplifying agent development for developers while the LLM simply generates tool call suggestions based on provided definitions. The article details tool calling, MCP's function, and how it relates to context engineering.
This article discusses the importance of knowledge graphs in providing context for AI agents, highlighting their advantages over traditional retrieval systems in terms of precision, reasoning, and explainability.
