Papersby GlyphHybrid Reasoning Agents research paper by Stanford University, 2026
Stanford University · Reasoning · Oct 13, 2026 · 41 upvotes · unverified
What it shows
This paper introduces an agent architecture that dynamically switches between latent reasoning and text-based interaction to improve performance and inference speed.
By Jiaru Zou, Yunzhe Qi, Sirui Chen and 5 more · arXiv 2610.18861 · PDF · Code
UnverifiedSummarised by a model from the abstract; not yet checked by hand.
More from Stanford University
All 12Thinking Inertia: LLMs Keep Thinking When Told Not ToThis paper shows that explicit controls often fail to stop LLMs from generating internal reasoning traces, a phenomenon the authors call thinking inertia.
Stanford University244 upvotesRead →Stateless Language Agents: Scaling Long-Horizon Automated ResearchThis paper introduces a framework where agents remain stateless, allowing a central harness to manage research state and improve long-horizon task efficiency.Stanford University1 citations30 upvotesRead →FAMOS: Feed-Forward 3D Articulation Modeling from Sparse ObservationsFAMOS is a feed-forward model that predicts articulated object motion from sparse point cloud observations.Stanford University40 upvotesRead →AISPA: User-Centric System Prompt Auditing for Large Language Model ApplicationsAISPA is a framework for auditing system prompts in commercial AI products to ensure they are protective of users.Stanford University36 upvotesRead →Recursive Multi-Agent SystemsRecursiveMAS extends recursive scaling principles from single models to multi-agent systems, enabling collaborative reasoning through iterative latent-space computations with improved efficiency and accuracy.Stanford University12 citations235 upvotesRead →Multi-User Large Language Model AgentsMulti-user large language model agents face challenges in handling conflicting objectives, privacy preservation, and coordination efficiency in multi-principal decision-making scenarios.Stanford University9 citations28 upvotesRead →Learning to Discover at Test TimeTest-time training enables AI systems to discover optimal solutions for specific scientific problems through continual learning focused on individual challenges rather than generalization.Stanford University118 citations45 upvotesRead →In-the-Flow Agentic System Optimization for Effective Planning and Tool UseAgentFlow, a trainable agentic framework with in-the-flow optimization, enhances reasoning in large language models by coordinating specialized modules and outperforms top baselines across various tasks.Stanford University76 citations113 upvotesRead →
Other reasoning papers
TopicChain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.
Google23.8k citations16 upvotesRead →DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsDeepSeekMath 7B improves mathematical reasoning through enhanced data pre-training and Group Relative Policy Optimization, achieving high scores on MATH benchmark without external tools.
DeepSeek10.6k citations152 upvotesRead →DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningReinforcement learning taught a model long step-by-step reasoning on par with OpenAI o1.DeepSeek5,972 citations458 upvotesRead →DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code IntelligenceDeepSeek-Coder-V2, a Mixture-of-Experts language model, excels in code-specific tasks by enhancing coding and mathematical reasoning capabilities while expanding language support and context length.DeepSeek530 citations73 upvotesRead →MolmoAct: Action Reasoning Models that can Reason in SpaceAction Reasoning Models (ARMs) integrate perception, planning, and control to enable adaptable and explainable robotic behavior, achieving superior performance across various tasks and settings.
Ai2232 citations45 upvotesRead →ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent PlanningThinkAct, a dual-system framework, uses reinforced visual latent planning to enable few-shot adaptation, long-horizon planning, and self-correction in embodied AI tasks by bridging high-level reasoning with low-level action execution.
NVIDIA192 citations43 upvotesRead →
About this paper
- Citations
- Not counted yet · Semantic Scholar
- Upvotes
- 41 · Hugging Face
- Lab
- Stanford University
Changes
Hugging Face upvotes fell from 44 to 41.
Hugging Face upvotes rose from 36 to 44.
Hugging Face upvotes rose from 32 to 36.
This paper introduces an agent architecture that dynamically switches between latent reasoning and text-based interaction to improve performance and inference speed.
Found by the weekly Hugging Face scan; not yet checked by hand.