Object-Oriented World Modeling (OOWM) is a novel framework addressing the limitations of Chain-of-Thought prompting in embodied tasks. It structures embodied reasoning and robotic planning by redefining the world model as an explicit symbolic tuple and leveraging software engineering formalisms like UML.
O artigo analisa a interação entre Chain-of-Thought (CoT) e Reinforcement Learning (RL) na geração de imagens a partir de texto (T2I) usando uma análise sistemática baseada em entropia. Ele revela que menor entropia dos tokens de imagem e do CoT textual se correlaciona com melhor qualidade de imagem, propondo a estratégia Entropy-Guided Group Relative Policy Optimization (EG-GRPO) para otimização com base na incerteza.
This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation rather than faithful surface chain-of-thought (CoT). It formalizes three competing hypotheses regarding the primary object of reasoning, impacting claims about faithfulness, interpretability, and benchmarks.
Sequence-Level PPO (SPPO) addresses the limitations of standard token-level PPO in long-horizon LLM reasoning tasks by reformulating the process as a Sequence-Level Contextual Bandit problem. This approach uses a decoupled scalar value function to derive low-variance advantage signals, offering improved sample efficiency and stability without the high computational overhead of critic-free alternatives.
The text explores how Chain-of-Thought (CoT) has evolved from an external prompt engineering technique to an internal reasoning capability in advanced AI models. Research indicates that applying external CoT to these models is now ineffective, as the reasoning process has been internalized.
This research proposes that LLM reasoning is a dynamic decoding state, not a static property, observable through early-stage entropy dynamics during generation. Tasks benefiting from Chain-of-Thought exhibit consistent entropy reduction, interpreted as a phase-transition to a structured reasoning regime.
Este artigo propõe o DLR, um framework de raciocínio latente reforçado para Vision-Language Models (VLMs) que melhora o raciocínio visual complexo, superando a perda de informação em CoT textual. Ele decompõe dinamicamente consultas, extrai latentes visuais e deduz respostas, oferecendo maior interpretabilidade e superando baselines em benchmarks vision-centric.
Este artigo propõe um método baseado em topologia para otimizar cadeias de raciocínio em LLMs, visando superar lacunas lógicas e custos elevados. Ele quantifica características estruturais de CoT, ToT e GoT usando homologia persistente para aprimorar o paradigma CoT.
This research paper introduces 'PathCal', investigating the distinct functional roles and timing of reflection markers in Large Reasoning Language Models' Chain-of-Thought trajectories. It reveals that markers like 'wait' or 'but' differ significantly in their impact on accuracy and generation length, challenging previous coarse-grained approaches.
This research paper introduces a controlled-invariance methodology for hallucination detection in large language models. Using oracle tests like extsc{Force} and extsc{Remove}, it investigates whether detection methods evaluate reasoning or merely surface correlates of the final answer.