proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersSehee Kim, Yumin Choi, Minki Kang1 min readpaperadvanced

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

Read on arxiv.org

Summary

EvolveTrade is a framework for self-evolving LLM trading agents that refines their tool-use policies (system prompts) based on past performance. It demonstrates improved Sharpe Ratio and Cumulative Return compared to agents with static policies across various market regimes.

  • LLM trading agents often use static, hand-written tool-use policies, limiting adaptability to market changes.
  • EvolveTrade treats the LLM agent's system prompt as a text-parameterized policy, refined by a separate Policy Agent.
  • Policy refinement uses accumulated decision traces and realized portfolio feedback, keeping the backbone LLM fixed.
  • This approach improves Sharpe Ratio and Cumulative Return over fixed-policy LLM baselines in most evaluated settings.

Engineers building adaptive LLM agents, especially in dynamic environments like financial markets, should care about this approach to policy refinement.

7/10
llmmachine learningreinforcement learningfinanceagent systems

Related reading

  1. COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

    COBRA‑Skills uses a contextual‑bandit loop to selectively evaluate and evolve LLM agent skills, achieving better performance with roughly half the evaluation cost of prior methods. The framework works with limited examples and remains robust across different agent setups and even when the target model creates its own skills.

    Hugging Face Daily Papersarxiv.org1 minpaper

  4. Modernizing the Trade Lifecycle With Governed Data and AI

    Databricks argues that modernizing the trade lifecycle now hinges on building a governed, real‑time data foundation that spans research, trading, risk, ops and compliance, rather than isolated AI pilots. Starting with a few high‑value questions—execution cost, shock risk, exception rates—and using Unity Catalog and Agent Bricks lets firms achieve measurable speed and auditability gains before sca…

    Databricksdatabricks.com5 min

  5. Your Agent Aced the Task. Will It Do It Again?

    The post introduces the Consistency Analyzer, a cheap black‑box diagnostic that flags flip‑prone decision steps in LLM agent traces, and shows how feeding the resulting consistency guidelines back into ALTK‑Evolve halves the gap between mean success and all‑run success (Pass⁵) on the AppWorld benchmark without hurting average accuracy.

    Hugging Facehuggingface.co8 minHN21

  6. RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

    RetireOPD introduces a self‑retiring on‑policy distillation framework for multi‑turn RL agents. A skill‑conditioned teacher is first trained with environment rewards, then a skill‑free student learns jointly via RL and token‑level distillation. The student automatically drops the teacher once its performance gap stops shrinking and it reaches a target success‑rate fraction, after which training c…

    Hugging Face Daily Papersarxiv.org1 minpaper