TechniqueRLHF / Alignment8 recent entries8 Oct 2026Empowering SMBs to do more with GeminiToday, we announced the new Gemini agent, your single, universal agent for work. For small and midsize businesses, with lean teams and margins, Gemini will be a critical tool for you to operate effici→8 Oct 2026Coding-Agent Benchmarks Should Match Their Users' Task FlowsarXiv:2610.09633v1 Announce Type: cross Abstract: The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engin→
TechniqueRAG8 recent entries2 Oct 2026LLM-based Agentic Reasoning Frameworks: A Survey from Methods to ScenariosarXiv:2508.17692v2 Announce Type: replace Abstract: Recent advances in LLM-based agents highlight the importance of their reasoning frameworks, which guide the problem-solving process in diverse ways.→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→5 Oct 2026On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI TutorarXiv:2610.02510v1 Announce Type: new Abstract: Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dial→6 Oct 2026NeuroCBIR: A Fast and Accurate Image Retrieval System for Whole-Brain and Region-Specific MRIarXiv:2610.06502v1 Announce Type: new Abstract: Content-based image retrieval (CBIR) in neuroimaging enables the identification of structurally similar brain scans, supporting diagnosis, prognosis, an→6 Oct 2026Announcing MCP Toolbox Java SDK v1.0: Agentic data access for the enterpriseCo-authors:Stenal Jolly, Strategic Cloud Engineer, GoogleAnubhav Dhawan, Software Engineer, Google Following the landmark announcement of MCP Toolbox v1.0, we're thrilled to announce that the MCP Tool→8 Oct 2026Liquid AI builds personal AI around device-level contextOn-device personal AI requires models and agent software that can operate within fixed hardware limits. Developers also need ways to keep those systems improving after deployment. Model builders are r→9 Oct 2026MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuningarXiv:2610.11727v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific →9 Oct 2026Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent SystemarXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-au
TechniqueAgents8 recent entries12 Oct 2026ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction AgentsarXiv:2610.13395v1 Announce Type: cross Abstract: Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to ge→12 Oct 2026Proactive Agentic OrchestrationarXiv:2610.13485v1 Announce Type: new Abstract: Agentic orchestration delegates tasks to sub-agents with independent contexts, providing a key path to extending the effective execution horizon of larg→12 Oct 2026Introducing DigitalOcean Insights: Built-in Observability for Your Agents, Applications, and InfrastructureCoding agents have changed how fast teams ship, and more of the software they ship now includes agents. A production agent spans model calls, routing decisions, tools, and the infrastructure underneat→12 Oct 2026Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software DevelopmentarXiv:2610.13022v1 Announce Type: cross Abstract: As LLMs become increasingly capable of implementing software, a critical bottleneck emerges: whether they truly understand what users want. Users ofte→12 Oct 2026Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull RequestsarXiv:2610.12849v1 Announce Type: cross Abstract: Current software engineering agents are evaluated predominantly inside isolated sandboxes against synchronous local tests. However, deploying features→12 Oct 2026Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE AgentsarXiv:2610.12598v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary→12 Oct 2026AgentSWE: Can Coding Agents Build the Agent You Actually Want?arXiv:2610.13361v1 Announce Type: cross Abstract: As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their us→12 Oct 2026Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market AnalysisarXiv:2610.13273v1 Announce Type: cross Abstract: API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generati
TechniqueFine-tuning8 recent entries7 Oct 2026AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World ModelarXiv:2610.08773v1 Announce Type: cross Abstract: Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent →8 Oct 2026SEER: Self-Enhancing Chain-of-Thought Compression for Reasoning ModelsarXiv:2509.14093v3 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting can substantially improve the reasoning ability of large language models (LLMs), but it often comes with high→8 Oct 2026Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance SegmentationarXiv:2610.10324v1 Announce Type: new Abstract: Pretrained models for cell and nuclear instance segmentation differ substantially in architecture, pretraining data and objectives, parameter count, inf→9 Oct 2026Revisiting Handcrafted Minutiae Detection: A Simple and Effective Open Source Baseline for Modern Fingerprint WorkflowsarXiv:2610.11641v1 Announce Type: new Abstract: Handcrafted minutiae detection algorithms remain fundamental to biometric science and forensic practice due to their full auditability, adherence to int→9 Oct 2026Qwen 3.8 Flash Next-GSQ-RCO-IQ2_XS at ~21 tok/s on just an RTX 3060 12GB + 16GB DDR4 RAM(No gate pruning, 100% bit-exact)(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next →9 Oct 2026MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuningarXiv:2610.11727v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific →12 Oct 2026SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent TrajectoriesarXiv:2610.13356v1 Announce Type: new Abstract: Coding agents are increasingly deployed for end-to-end software engineering tasks, where a readily available oracle evaluator that defines the success c→12 Oct 2026ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction AgentsarXiv:2610.13395v1 Announce Type: cross Abstract: Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to ge
TechniqueMultimodal8 recent entries4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→6 Oct 2026For their Mistral Large 4 release, @MistralAI ran a blind Surge human eval, with our expert software engineers evaluating five frontier mode…For their Mistral Large 4 release, @MistralAI ran a blind Surge human eval, with our expert software engineers evaluating five frontier models on coding quality. Le Chonk ranked #1 among open-weight m→7 Oct 2026Why is ik_llama.cpp said to be faster than Mainline? On my hybrid multi-GPU rig, Mainline easily beats itI constantly see recommendations saying that ik_llama.cpp (ikawrakow's fork) is the undisputed king of hybrid CPU/GPU offloading and MoE performance. However, every time I benchmark it against mainlin→7 Oct 2026We @sequoia are thrilled to lead @MeckaAI’s Series B. AI took the digital world by storm; bringing it into the physical world will be a wave…We @sequoia are thrilled to lead @MeckaAI’s Series B. AI took the digital world by storm; bringing it into the physical world will be a wave at least as large, but harder - it demands excellence acros→8 Oct 2026Welcome to Gemini at Work 2026: Introducing the Gemini agentEditor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your →8 Oct 2026MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive ScreeningarXiv:2610.10448v1 Announce Type: cross Abstract: MemoCare is an interactive mobile system for automated multimodal cognitive screening. A React Native application combines spoken responses, temporal →11 Oct 2026Microsoft unveils Microsoft-Decision-1, a fast decision-scoring model trained on Qwen3.5-9B, and says it will soon rebase it on MAI, OpenAI, and other models (Achint Srivastava/Command Line)Achint Srivastava / Command Line: Microsoft unveils Microsoft-Decision-1, a fast decision-scoring model trained on Qwen3.5-9B, and says it will soon rebase it on MAI, OpenAI, and other models — Decisi→12 Oct 2026Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill InductionarXiv:2610.12984v1 Announce Type: new Abstract: Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human domain knowledge remain challengin
TechniqueSafety8 recent entries7 Oct 2026Behavioral Safety Assessment towards Large-scale Deployment of Autonomous Vehicles, Part I: MethodologyarXiv:2610.08450v1 Announce Type: new Abstract: Autonomous vehicles (AVs) have significantly advanced in real-world deployment in recent years, yet safety continues to be a critical barrier to widespr→7 Oct 2026An Empirical Fault Vulnerability Exploration of ReRAM-based Process-in-Memory CNN AcceleratorsarXiv:2610.07029v1 Announce Type: cross Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive →8 Oct 2026Welcome to Gemini at Work 2026: Introducing the Gemini agentEditor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your →8 Oct 2026A Framework for the Systematic Review of ML Assets in AI RegistriesarXiv:2610.09551v1 Announce Type: new Abstract: Background: Modern software systems increasingly rely on Machine Learning (ML) assets (i.e., pre-trained models, datasets, benchmarks) for building, eva→9 Oct 2026TACROSS: An Efficient and Low-Cost Scalable Human Touch System Across Heterogeneous Tactile Sensors for Dexterous Robot LearningarXiv:2610.11945v1 Announce Type: cross Abstract: Collecting tactile demonstrations on robots is costly and slow, motivating the use of lower-cost human tactile gloves for scalable data collection. Ho→9 Oct 2026Closed-loop evaluation of LLM agents for embedded software developmentarXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair s→12 Oct 2026Proactive Agentic OrchestrationarXiv:2610.13485v1 Announce Type: new Abstract: Agentic orchestration delegates tasks to sub-agents with independent contexts, providing a key path to extending the effective execution horizon of larg→12 Oct 2026Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE AgentsarXiv:2610.12598v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary