Papersby Glyph

Notable data and AI papers

Papers627 Labs45

627 papers · 45 labs

SkillOpt: Executive Strategy for Self-Evolving Agent Skills research paper by Microsoft, 2026

Microsoft · Agents and evaluation · May 22, 2026 · 173 citations · 263 upvotes · unverified

SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.

By Yifan Yang, Ziyang Gong, Weiquan Huang and 12 more · arXiv 2605.23904 · PDF · Code

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

More from Microsoft

Agents and evaluationUnverifiedNov 2, 2026WebHarbor: Docking Real Websites for Evolving GUI Agent EnvironmentsWebHarbor provides realistic, containerized website environments for training and testing computer-using web agents across complex online tasks.

Microsoft28 upvotesRead →Agents and evaluationUnverifiedOct 19, 2026Agent World Model in the Wild: Computer-Use Agent Environment SynthesisThis pipeline creates controllable, open-source environments to safely train and test AI agents on complex, long-horizon computer-use tasks.

Microsoft69 upvotesRead →Training and scalingUnverifiedOct 16, 2026Self-Evolving Coding Agents via Harness-Policy OptimizationThis framework improves coding agents by recursively alternating between optimizing the agent's policy and the environment harness it uses to interact with code.

Microsoft48 upvotesRead →Multimodal and roboticsUnverifiedOct 13, 2026AesCode: Aesthetic Code Generation with Decoupled Cross-Modal RewardsThis paper introduces a method to improve code-based visual generation by using image-based aesthetic guidance and decoupled rewards to ensure quality and correctness.

Microsoft137 upvotesRead →Training and scalingUnverifiedOct 13, 2026APT: Feedback-Driven Agentic Post-Training for Text-to-Image GenerationThis paper introduces an automated post-training framework that uses a feedback loop of evaluation and diagnosis to improve text-to-image models.

Microsoft23 upvotesRead →Multimodal and roboticsUnverifiedOct 13, 2026LensErase: A Foundation Model for Erase AnythingThis paper introduces a foundation model designed for versatile image editing and object removal using mask-based inputs and efficient positional encoding.

Microsoft52 upvotesRead →Inference and efficiencyUnverifiedOct 13, 2026Simplifying and Improving On-Policy Distillation for Few-Step DiffusionThis paper introduces a simplified regression-based method for distilling diffusion models that improves generation speed without requiring complex training techniques.

Microsoft27 upvotesRead →Applied AIUnverifiedOct 5, 2026MiniCorp: The Last Mile of the AI Agent FirmMiniCorp is an office simulator that allows researchers to study how agents run companies and generate enterprise data for training.

Microsoft39 upvotesRead →

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: arXiv.org
Citations: 173, 37 influential · Semantic Scholar
Upvotes: 263 · Hugging Face
Lab: Microsoft · on Companies · on Acquisitions · on Quarterly · on Paydays · on Releases · on TechConf

Changes

CitationsNov 9, 2026Citations rose from 167 to 173.

CitationsNov 2, 2026Influential citations rose from 30 to 37.

CitationsNov 2, 2026Citations rose from 133 to 167.

CitationsOct 12, 2026Influential citations rose from 23 to 30.

CitationsOct 12, 2026Citations rose from 116 to 133.

CitationsOct 5, 2026Influential citations rose from 17 to 23.

CitationsOct 5, 2026Citations rose from 89 to 116.

CitationsSep 28, 2026Citations rose from 85 to 89.

CitationsSep 25, 2026A first count of 17 influential citations.

CitationsSep 25, 2026A first count of 85 citations.

New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.