Guohao Li 🐫(@guohao_li):"behavioral state decay": the failure mode that long-horizon agents forget what matters. meta ai's fix: a memory agent that updates the memory bank and then decides whether to emit a proactive intervention. they train qwen3.5-27b on seta using sft and grpo and show gains on terminal-bench 2.0. great to see seta terminal agent rl envs used this way - remember when it matters by meta ai @yifannnwu @zhuokaiz: https://t.co/REP5XMxUVJ

Guohao Li 🐫

@guohao_li

Founder @Eigent_AI / @CamelAIOrg. Scaling RL Environments for Agents. Prev Oxford, KAUST, ETHz, Intel, Kumo.

加入 August 2018

5.4K 正在關注 14.9K 粉絲

Guohao Li 🐫@guohao_li

2026.07.13 12:39

"behavioral state decay": the failure mode that long-horizon agents forget what matters. meta ai's fix: a memory agent that updates the memory bank and then decides whether to emit a proactive intervention. they train qwen3.5-27b on seta using sft and grpo and show gains on terminal-bench 2.0. great to see seta terminal agent rl envs used this way - remember when it matters by meta ai @yifannnwu @zhuokaiz: - our seta project: