EvoForge通过群体进化与知识共享机制，将单智能体优化升级为系统级自我进化流程，实现性能倍增与稳定提升。
evolve.md — God of Agents instructions + population management
agent.py — single-file harness under test
editable harness section — prompt, registries, tools, routing
fixed adapter section — Harbor integration + trajectory serialization
program.md — meta-agent instructions + directive
.agent/ — optional agent workspace artifacts
docs/ — skills (Semantic Observability, Knowledge Sharing) for EvoForge
jobs/ — Harbor job outputs
results.tsv — experiment log (created by meta-agent, gitignored)
run.log — latest run output
* evolve.md：定义种群规模、进化策略（谁留下、谁变异、谁交叉）
* program.md：定义 meta-agent 如何修改 agent.py
* agent.py：真正被优化的对象
docs/trace-analysis.md
docs/knowledge-sharing.md
mutate population → run benchmark → evaluate → keep or discard → repeat
tasks/my-task/
task.toml — config (timeouts, metadata)
instruction.md — prompt sent to the agent
tests/
test.sh — entry point, writes /logs/reward.txt
test.py — verification (deterministic or LLM-as-judge)
environment/
Dockerfile — task container (FROM autoagent-base)
files/ — reference files mounted into container
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容，请联系我们，一经查实，本站将立刻删除。
如需转载请保留出处：https://51itzy.com/kjqy/267989.html