Papersby GlyphStateless Language Agents: Scaling Long-Horizon Automated Research research paper by Stanford University, 2026
Stanford University · Agents and evaluation · Oct 6, 2026 · 1 citations · 30 upvotes · unverified
What it shows
This paper introduces a framework where agents remain stateless, allowing a central harness to manage research state and improve long-horizon task efficiency.
By Qizheng Zhang, Changxiu Ji, Isaac Sun and 15 more · arXiv 2610.07625 · PDF · Code
UnverifiedSummarised by a model from the abstract; not yet checked by hand.
More from Stanford University
All 12Hybrid Reasoning AgentsThis paper introduces an agent architecture that dynamically switches between latent reasoning and text-based interaction to improve performance and inference speed.
Stanford University41 upvotesRead →Thinking 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 →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 agents and evaluation papers
TopicGemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic CapabilitiesGemini 2.X model family, including Gemini 2.5 Pro and Flash, offers superior coding, reasoning, and multimodal understanding capabilities across a range of computational efficiencies.
Google4,594 citations67 upvotesRead →DeepSeek-V3.2: Pushing the Frontier of Open Large Language ModelsDeepSeek-V3.2 introduces DeepSeek Sparse Attention and a scalable reinforcement learning framework, achieving superior reasoning and performance compared to GPT-5 and Gemini-3.0-Pro in complex reasoning tasks.
DeepSeek887 citations275 upvotesRead →WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?WorkArena and BrowserGym evaluate large language model-based agents' ability to perform enterprise software tasks, revealing gaps in current agent capabilities and differences between open and closed-source LLMs.
ServiceNow443 citations2 upvotesRead →Aya Model: An Instruction Finetuned Open-Access Multilingual Language ModelAya, a multilingual generative language model supporting over 50% lower-resourced languages, excels in both generative and discriminative tasks across 99 languages, and provides extensive evaluations and open-source resources.
Cohere438 citations48 upvotesRead →Rubrics as Rewards: Reinforcement Learning Beyond Verifiable DomainsRubrics as Rewards (RaR) framework uses structured rubrics as interpretable reward signals for on-policy training, improving performance in real-world reinforcement learning tasks with subjective criteria.
Scale AI431 citations6 upvotesRead →SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?SWE-Bench Pro is a challenging benchmark for coding models, featuring complex, enterprise-level problems that require substantial code modifications, with performance evaluations showing significant limitations in current models.Scale AI367 citations21 upvotesRead →
About this paper
- Citations
- 1, 0 influential · Semantic Scholar
- Upvotes
- 30 · Hugging Face
- Lab
- Stanford University
Changes
A first count of 0 influential citations.
A first count of 1 citations.
This paper introduces a framework where agents remain stateless, allowing a central harness to manage research state and improve long-horizon task efficiency.
Found by the weekly Hugging Face scan; not yet checked by hand.