Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use research paper by Stanford University, 2025

Stanford University · Agents and evaluation · Oct 7, 2025 · 76 citations · 113 upvotes · unverified

Read on arXiv

What it shows

AgentFlow, 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.

By Zhuofeng Li, Haoxiang Zhang, Seungju Han and 6 more · arXiv 2510.05592 · PDF · Code

UnverifiedHugging Face's summary; not yet checked by hand.

More from Stanford University

All 12
ReasoningUnverifiedOct 13, 2026Hybrid 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 →ReasoningUnverifiedOct 8, 2026Thinking 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 →Agents and evaluationUnverifiedOct 6, 2026Stateless 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 →Multimodal and roboticsUnverifiedSep 17, 2026FAMOS: 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 →Alignment and safetyUnverifiedJul 30, 2026AISPA: 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 →Agents and evaluationUnverifiedApr 28, 2026Recursive 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 →Foundation modelsUnverifiedMar 19, 2026Multi-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 →Retrieval and dataUnverifiedJan 22, 2026Learning 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 →

Other agents and evaluation papers

Topic
Agents and evaluationUnverifiedJul 7, 2025Gemini 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 →Agents and evaluationUnverifiedDec 2, 2025DeepSeek-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 →Agents and evaluationMar 12, 2024WorkArena: 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 →Agents and evaluationFeb 12, 2024Aya 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 →Agents and evaluationJul 23, 2025Rubrics 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 →Agents and evaluationSep 21, 2025SWE-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
Venue
International Conference on Learning Representations
Citations
76, 8 influential · Semantic Scholar
Upvotes
113 · Hugging Face
Lab
Stanford University

Changes

CitationsNov 2, 2026Influential citations rose from 7 to 8.
CitationsNov 2, 2026Citations rose from 69 to 76.
CitationsOct 12, 2026Citations rose from 65 to 69.
CitationsOct 5, 2026Influential citations rose from 5 to 7.
CitationsOct 5, 2026Citations rose from 59 to 65.
CitationsSep 28, 2026Citations rose from 58 to 59.
CitationsSep 25, 2026A first count of 5 influential citations.
CitationsSep 25, 2026A first count of 58 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.