提出自进化元认知策略优化方法，让LLM红队测试更智能高效地发现安全漏洞。
arXiv:2605.10067v3 Announce Type: replace-cross Abstract: Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). Whil…
提出单向策略优化方法，让大模型在无外反馈下自我进化，提升推理与对齐能力。
arXiv:2605.22156v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling re…
策略优化新范式：训练阶段注入多样性，显著提升测试时搜索性能
arXiv:2605.22817v1 Announce Type: cross Abstract: Language models must now generalize out of the box to novel environments and work inside inference-s…
提出LambdaPO框架，用lambda算子优化推理语言模型策略，显著提升逻辑推理能力。
arXiv:2605.19416v1 Announce Type: new Abstract: Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning ali…
LLM回测中时间泄漏的顽疾有了新解法，TEMPO通过模式分离策略优化确保评估可信度
arXiv:2605.18843v1 Announce Type: new Abstract: Backtesting large language models on historical events requires reasoning exclusively from information…
提出采样式权重空间投影方法，高效解决约束策略优化问题，已被IFAC 2026收录
arXiv:2512.13788v2 Announce Type: replace Abstract: Safety-critical learning requires policies that improve performance without leaving the safe opera…
COOPO算法提出循环离线-在线策略优化，巧妙解决分布偏移与灾难性遗忘难题，为强化学习混合范式带来新突破。
arXiv:2605.18675v1 Announce Type: new Abstract: Offline reinforcement learning struggles with distributional shift and constrained performance due to …
用结构化模板引导强化学习，让LLM推理训练告别低效自采样，提升策略可迁移性。
arXiv:2505.15692v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoni…
提出序数分解离散奖励的ODRPO方法，提升LLM对齐中策略优化的鲁棒性，直面自动评分器的随机挑战。
arXiv:2605.12667v2 Announce Type: replace-cross Abstract: The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedba…