Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper presents EvolveTrade, which treats a trading agent's system prompt as its policy. After each trading interval, a separate Policy Agent reads the decision traces and the realized returns and rewrites the prompt. The backbone model stays frozen. Across several market regimes and two backbone models, the evolved agent beats fixed-prompt baselines on Sharpe ratio and cumulative return in most settings. The rewritten prompts also led the agent to run more code-based analysis and to compute signals that fit the current market regime. Paper:

Cool Hermes agent use case to unlock productivity: Nous Research has a complete catalog of Hermes agentic skills. Instead of scrolling through them all manually, just tell your Hermes agent to do it for you - based on what it thinks would be helpful to you. Prompt: "Based on my existing workflows, scan [ and identify 5-10 agent skills that could genuinely change how I work. Summarise your top picks, and deliver it in a report so I can then manually approve what you can install." Once installed, you can then have your agent modify the skills to your exact needs. Low-hanging fruit, but it works so well.

Cooling supplier AVC began seeing a small revenue contribution from Vera Rubin in September, according to Citi. The bank expects shipments to ramp up in Q4 2026. At Auras, Citi expects Vera Rubin inner and rack manifolds to support Q4 revenue growth. Its cold plates for the platform are still undergoing qualification.