Imagen de Portada

Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Alderete, John, Benthal, Sebastian, Xu, Connie, Xing, John
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
por: Meherab, Md Muntaqim, et al.
Publicado: (2026)

Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization
por: Liu, Shengchao, et al.
Publicado: (2025)

Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring
por: Ayoughi, Melika, et al.
Publicado: (2025)

Identity Bridge: Enabling Implicit Reasoning via Shared Latent Memory
por: Lin, Pengxiao, et al.
Publicado: (2025)

CausalARC: Abstract Reasoning with Causal World Models
por: Maasch, Jacqueline, et al.
Publicado: (2025)

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
por: Zhou, Yang, et al.
Publicado: (2025)

CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
por: Bonagiri, Akash, et al.
Publicado: (2026)

Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
por: Wang, Shengjie, et al.
Publicado: (2026)

Language Agents Meet Causality -- Bridging LLMs and Causal World Models
por: Gkountouras, John, et al.
Publicado: (2024)

Restructuring Tractable Probabilistic Circuits
por: Zhang, Honghua, et al.
Publicado: (2024)

InsightBuild: LLM-Powered Causal Reasoning in Smart Building Systems
por: Neogi, Pinaki Prasad Guha, et al.
Publicado: (2025)

The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models
por: Anderson, Samuel Cyrenius
Publicado: (2026)

Choosing How to Remember: Adaptive Memory Structures for LLM Agents
por: Lu, Mingfei, et al.
Publicado: (2026)

Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space
por: Vasilenko, Vladimir
Publicado: (2026)

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
por: Zhang, Xichen, et al.
Publicado: (2025)

MALT: Improving Reasoning with Multi-Agent LLM Training
por: Motwani, Sumeet Ramesh, et al.
Publicado: (2024)

AgentKit: Structured LLM Reasoning with Dynamic Graphs
por: Wu, Yue, et al.
Publicado: (2024)

Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents
por: Liu, Tennison, et al.
Publicado: (2025)

Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning
por: Altabaa, Awni, et al.
Publicado: (2025)

Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction
por: Qu, Zhan, et al.
Publicado: (2026)

Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
por: Zhao, Yuze, et al.
Publicado: (2025)

Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
por: Shen, ChengAo, et al.
Publicado: (2024)

Hypothesis Network Planned Exploration for Rapid Meta-Reinforcement Learning Adaptation
por: Jacobson, Maxwell Joseph, et al.
Publicado: (2023)

Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
por: Schneider, Chris, et al.
Publicado: (2026)

Evaluating Long-Context Reasoning in LLM-Based WebAgents
por: Chung, Andy, et al.
Publicado: (2025)

Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning
por: Wienöbst, Marcel, et al.
Publicado: (2025)

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
por: Shan, Lianlei, et al.
Publicado: (2026)

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
por: Zhai, Zhiyuan, et al.
Publicado: (2026)

Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction
por: Rushing, Bruce
Publicado: (2024)

Experiential Reflective Learning for Self-Improving LLM Agents
por: Allard, Marc-Antoine, et al.
Publicado: (2026)

The Dual-State Architecture for Reliable LLM Agents
por: Thompson, Matthew
Publicado: (2025)

Enabling Agents to Communicate Entirely in Latent Space
por: Du, Zhuoyun, et al.
Publicado: (2025)

Hypothesis Testing the Circuit Hypothesis in LLMs
por: Shi, Claudia, et al.
Publicado: (2024)

Agile Reinforcement Learning through Separable Neural Architecture
por: Mostakim, Rajib, et al.
Publicado: (2026)

From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
por: Ferrag, Mohamed Amine, et al.
Publicado: (2025)

Caracal: Causal Architecture via Spectral Mixing
por: Gan, Bingzheng, et al.
Publicado: (2026)

How to Train Your LLM Web Agent: A Statistical Diagnosis
por: Vattikonda, Dheeraj, et al.
Publicado: (2025)

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
por: Liu, Jiaqi, et al.
Publicado: (2026)

A Technical Exploration of Causal Inference with Hybrid LLM Synthetic Data
por: Kim, Dana, et al.
Publicado: (2025)

Hypothesis Search: Inductive Reasoning with Language Models
por: Wang, Ruocheng, et al.
Publicado: (2023)