cs.AI（2025-09-03）

📊 共 7 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning	提出HICRA算法，通过强化学习提升LLM的层级推理能力，优化策略规划。	reinforcement learning large language model
2	The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs	揭示LLM人格幻觉：自述与行为的解离现象研究	RLHF large language model
3	CausalARC: Abstract Reasoning with Causal World Models	提出CausalARC，用于在低数据和分布偏移下进行因果抽象推理。	world model
4	Language Models Do Not Follow Occam's Razor: A Benchmark for Inductive and Abductive Reasoning	提出InAbHyD基准测试LLM的归纳和溯因推理能力，发现其不遵循奥卡姆剃刀原则	world model large language model

#	题目	一句话要点	标签	🔗
5	ANNIE: Be Careful of Your Robots	ANNIE：针对具身AI系统的对抗性安全攻击研究与基准测试	embodied AI vision-language-action VLA	✅
6	Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation	揭示LLM智能体行为不一致性，质疑其在社会模拟中替代人类受试者的有效性	large language model
7	Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations	提出Embodied-LM，通过具身图式表征增强神经符号推理能力	large language model