文件最后提交记录最后更新时间
test(agent_evolving): Add agent evolving trainer unit tests Add agent evolving trainer unit tests Refs: #364 Co-authored-by: zhangzhongteng<zhangzhongteng1@huawei.com> # message auto-generated for no-merge-commit merge: !454 test(agent_evolving): Add agent evolving trainer unit tests From: @z2tng Reviewed-by: @deyang, @yangzequ See merge request: openJiuwen/agent-core!4543 个月前
refactor(agent_evolving): refactor agent_evolving (rename producer to updater) - Rename SingleDimProducer/MultiDimProducer to SingleDimUpdater/MultiDimUpdater - Rename UpdateProducer protocol to Updater - Rename produce() method to update() for consistency - Rename optimizer update() to step() for RL-like semantics - Rename producer_state to updater_state in checkpointing - Update tests, examples, and documentation accordingly Refs: #371 Co-authored-by: zhangzhongteng<zhangzhongteng1@huawei.com> # message auto-generated for no-merge-commit merge: !463 refactor(agent_evolving): refactor agent_evolving (rename producer to updater) From: @z2tng Reviewed-by: @deyang, @yangzequ See merge request: openJiuwen/agent-core!4633 个月前
refactor(agent_evolving): make optimizer base async and integrate EvolutionSignal - BaseOptimizer.backward() changed to async with _bad_signals filter - InstructionOptimizer fully async: _backward() precomputes, _step() sync - Updater protocol and Trainer updated for async calls Refs: #713 Co-authored-by: zhangzhongteng<zhangzhongteng1@huawei.com> # message auto-generated for no-merge-commit merge: !1083 refactor(agent_evolving): make optimizer base async and integrate EvolutionSignal From: @z2tng Reviewed-by: @deyang, @SnapeK See merge request: openJiuwen/agent-core!10831 个月前