Did Codex Reset
GitHub

EvolveTrade rewrites a trading agent's system prompt after each interval

DAIR.AI

The EvolveTrade paper treats a trading agent's system prompt as its policy. After each trading interval, a separate Policy Agent reads the decision traces and realized returns and rewrites the prompt. The backbone model stays frozen.

The paper reports that the evolved agent beat fixed-prompt baselines on Sharpe ratio and cumulative return in most settings, across several market regimes and two backbone models. The rewritten prompts also led the agent to run more code-based analysis and to compute signals that fit the current market regime.

#evolvetrade#ai-agents#system-prompts#trading#research

Only 35.8% of the cleanest public terminal-agent RL collection passed a Salesforce AI Research audit

Salesforce AI Research put that collection at 35.8% clean and two others at 10.1% and 3.3%, after finding reward errors in both directions. The authors say RIVER, which filters defective environments, increases RL gains by 106% on Terminal-Bench-Lite and 30% on Terminal-Bench v2.1 while using fewer than 30% of TMax's environments.