TechniqueRLHF / Alignment8 recent entries7 Oct 2026TAFFY: A Task-Adaptive Tabular Foundation Model with In-Context DiversityarXiv:2610.07559v1 Announce Type: new Abstract: Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with →7 Oct 2026Stabilizing language models under continual learning via condition-anchored distillationarXiv:2610.06940v1 Announce Type: new Abstract: Continual adaptation of language models can change their output distribution on prompts learned earlier, while retaining every old prompt-answer pair ma
TechniqueRAG8 recent entries12 Oct 2026Introducing DigitalOcean Agent Data Services: The Data Foundation for AgentsAgents are only as capable as the context they can reach. An agent with reliable access to the right information makes decisions grounded in fact; one without it guesses. And the work agents produce i→12 Oct 2026Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision SupportarXiv:2610.12666v1 Announce Type: cross Abstract: We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conv→12 Oct 2026Global Consistency Repair for Natural-Language Claim SetsarXiv:2601.13600v2 Announce Type: replace Abstract: NLP systems increasingly aggregate claims from retrieved passages, documents, and generated reasoning steps. Yet current factuality methods mostly v→12 Oct 2026GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence ReportsarXiv:2610.12617v1 Announce Type: new Abstract: Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate,→12 Oct 2026CopRoute: Dependence-Aware Conformal Routing for Language ModelsarXiv:2610.13276v1 Announce Type: new Abstract: Set-based language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the num→12 Oct 2026Can Language Models Play the Wikipedia Game?arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ→12 Oct 2026A 'free' multi-modal 'embedding' model (already) included with your LLM: vLLM plugin + upstream PRDisclaimer: I work for NuMind, the company behind this plugin. TLDR: Text/image (simili-)embeddings from the LLM you already have loaded :-) I've been working on making it easier to obtain embeddings →14 Oct 2026Discover AI: A Learning Guide - 51 hands-on labs for learning how AI actually works.This is an offline app with 51 hands-on labs for learning how AI actually works, from neurons to agents and more... **A bit of insight** - 51 labs in 6 groups, from the basics (what a neuron is, gradi
TechniqueAgents8 recent entries12 Oct 2026Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent …Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos→12 Oct 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAarXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-→12 Oct 2026LLC: lightweight Open WebUI alt now with Agents+MCP+RAG+Image EditingQuick context: LocalLightChat (LLC) is a chat frontend for local LLMs. Download it, run it, that's it. No installation (unless you want to), no dependencies, and it runs on pretty much anything, inclu→12 Oct 2026Introducing DigitalOcean Agent Data Services: The Data Foundation for AgentsAgents are only as capable as the context they can reach. An agent with reliable access to the right information makes decisions grounded in fact; one without it guesses. And the work agents produce i→12 Oct 2026Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision SupportarXiv:2610.12666v1 Announce Type: cross Abstract: We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conv→12 Oct 2026Global Consistency Repair for Natural-Language Claim SetsarXiv:2601.13600v2 Announce Type: replace Abstract: NLP systems increasingly aggregate claims from retrieved passages, documents, and generated reasoning steps. Yet current factuality methods mostly v→12 Oct 2026GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence ReportsarXiv:2610.12617v1 Announce Type: new Abstract: Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate,→14 Oct 2026Discover AI: A Learning Guide - 51 hands-on labs for learning how AI actually works.This is an offline app with 51 hands-on labs for learning how AI actually works, from neurons to agents and more... **A bit of insight** - 51 labs in 6 groups, from the basics (what a neuron is, gradi
TechniqueFine-tuning8 recent entries7 Oct 2026Enhancing High-order Interaction Awareness in LLM-based Recommender ModelarXiv:2409.19979v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated prominent reasoning capabilities in recommendation tasks by transforming them into text-generat→7 Oct 2026DrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree SearcharXiv:2507.07426v4 Announce Type: replace Abstract: Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning. However, their e→8 Oct 2026Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding ModelsarXiv:2610.10508v1 Announce Type: new Abstract: Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as→8 Oct 2026Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving CompressionarXiv:2610.09788v1 Announce Type: new Abstract: Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can inc→8 Oct 2026How Do LLMs Change Predictions Under Negation?arXiv:2610.09571v1 Announce Type: new Abstract: Negation is an essential feature of human language, yet large language models (LLMs) remain unreliable in processing it. We evaluate recent open-source →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 2026Qwen3.8-27B vs Frontier vs OthersHere're results from my final test of coding, coding (panda/numpy), data analysis, data-driven decision-making, and local RAG domains I interact with most often. This test, which is refined from a 500→14 Oct 2026Discover AI: A Learning Guide - 51 hands-on labs for learning how AI actually works.This is an offline app with 51 hands-on labs for learning how AI actually works, from neurons to agents and more... **A bit of insight** - 51 labs in 6 groups, from the basics (what a neuron is, gradi
TechniqueMultimodal8 recent entries7 Oct 2026Foveated Compression: Selective High-Resolution Preservation for Token-Efficient VLMsarXiv:2610.07729v1 Announce Type: new Abstract: Visual tokens are a major source of inference cost in vision-language models, yet simple image downsampling remains a surprisingly strong compression ba→8 Oct 2026TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence ReasoningarXiv:2610.09360v1 Announce Type: cross Abstract: Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts. Answering complex questions over such→9 Oct 2026RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip DesignarXiv:2610.10858v1 Announce Type: cross Abstract: Analog/RF circuits remain the critical interface between digital computation and the physical world, and emerging standards from Wi-Fi 7 to 6G place s→12 Oct 2026MHR-Router: Multimodal Heterogeneous Retrieval-Enhanced Adaptive Routing for VLM InferencearXiv:2610.13278v1 Announce Type: new Abstract: Vision-language models (VLMs) exhibit complementary capabilities, yet selecting the most suitable expert for a given image-question query remains challe→12 Oct 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAarXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-→12 Oct 2026Introducing DigitalOcean Agent Data Services: The Data Foundation for AgentsAgents are only as capable as the context they can reach. An agent with reliable access to the right information makes decisions grounded in fact; one without it guesses. And the work agents produce i→12 Oct 2026Can Language Models Play the Wikipedia Game?arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ→12 Oct 2026A 'free' multi-modal 'embedding' model (already) included with your LLM: vLLM plugin + upstream PRDisclaimer: I work for NuMind, the company behind this plugin. TLDR: Text/image (simili-)embeddings from the LLM you already have loaded :-) I've been working on making it easier to obtain embeddings
TechniqueSafety8 recent entries5 Oct 2026Not Until the Evidence Says So: Teaching LLM Investigators When to Close a CasearXiv:2610.03190v1 Announce Type: cross Abstract: Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is e→5 Oct 2026CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented GenerationarXiv:2610.03421v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown strong visual reasoning abilities, but knowledge-intensive visual question answering often requires →5 Oct 2026b11430hexagon: matmul and flash-atten scalability updates (#29974) hexagon: head-parallel flash_attn partitioning for row-split multicore In row-split mode each core computes its output row shard of every M→6 Oct 2026Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio GenerationarXiv:2610.05768v1 Announce Type: cross Abstract: We ask: given a retrieved source audio S and a separate reference audio R, can we synthesize novel audio Y out of this pair (S,R) such that Y remains →6 Oct 2026Principled Top-k Selection for Language Models with Hybrid GradientsarXiv:2610.04162v1 Announce Type: new Abstract: Selecting the best k items out of m candidates is a critical component of modern large language model systems, such as document selection in Retrieval-A→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→7 Oct 2026RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG SystemsarXiv:2610.08571v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a ben→12 Oct 2026CopRoute: Dependence-Aware Conformal Routing for Language ModelsarXiv:2610.13276v1 Announce Type: new Abstract: Set-based language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the num