Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
EvoDS directly addresses two core failure modes of current LLM-based data science automation — static skill sets and context overflow — with a system that learns to expand its own capabilities and manage long-horizon context, achieving a 28.9% average improvement over existing open-source agents across four benchmarks.
The pattern directly addresses two concrete costs of long-running agent loops — context window exhaustion and API latency spikes — by combining caching, lazy schema loading, and model-role separation with an intermediate compaction step.
The post illustrates that MCP tool-catalog bloat can silently degrade Claude Code's tool selection accuracy, and that scoping servers to the project level and using a ranked-catalog gateway are concrete mitigations for the problem.
Developers running small local models can now use a structured coding agent without needing a large context window, making agentic workflows accessible on consumer hardware.
Developers building agentic pipelines should treat the context window as a finite budget — actively pruning, summarizing, and prioritizing what enters it to avoid compounding token costs and degraded reasoning across multi-step loops.
Developers using Claude Code with multiple MCPs and configuration files can now identify and eliminate unnecessary context consumption, freeing up tokens for actual coding work and improving response latency.
Apply the Principle of Least Context now — by routing all tool calls and file reads through isolated sub-agents and keeping the main orchestrator lean — to prevent context rot from silently degrading Claude Code's output quality on long-running tasks.