TechniqueRLHF / Alignment8 recent entries12 Oct 2026Byzantine-Resilient Federated Large Language Model via Hypergraph Message PassingarXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is→12 Oct 2026Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based ValidationarXiv:2610.12703v1 Announce Type: cross Abstract: High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation a
TechniqueRAG8 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 2026KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache ReusearXiv:2610.13060v1 Announce Type: new Abstract: KV-cache reuse in large language model serving is commonly limited to exact prompt prefixes, preventing reuse when the same retrieved document appears a→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 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 2026Enhancing Legal Reasoning in Pre-trained Language Models via Knowledge Graph-Guided Multi-Task Pre-trainingarXiv:2610.13722v1 Announce Type: new Abstract: Legal language understanding requires reasoning over semi-structured regulatory documents, yet standard pre-training objectives do not explicitly target→12 Oct 2026DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation DesignarXiv:2610.13116v1 Announce Type: new Abstract: As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce s→12 Oct 2026AgentTune: A Unified Training Lifecycle for Tool-Using LLM AgentsarXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing
TechniqueAgents8 recent entries12 Oct 2026AgentTune: A Unified Training Lifecycle for Tool-Using LLM AgentsarXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing →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 2026Agentic data science with the Data Agent KitImagine your compliance team notices that payments are taking longer than expected to clear. They suspect fraud, and you’re the data scientist helping figure out which transactions to investigate firs→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→12 Oct 2026A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPOarXiv:2610.13669v1 Announce Type: new Abstract: Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection becau→12 Oct 2026A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety AssurancearXiv:2610.13479v1 Announce Type: new Abstract: Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase s→12 Oct 2026A Baseline Assessment for the Agentic Web Technology StackarXiv:2610.13703v1 Announce Type: new Abstract: The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming t→12 Oct 202610 Years of the SRE book: Announcing the second edition of 'Site Reliability Engineering”A decade ago, Google released Site Reliability Engineering: How Google Runs Production Systems with O'Reilly Media. What began as a collection of our practices for managing large-scale infrastructure
TechniqueFine-tuning8 recent entries12 Oct 2026DeFM: Learning Foundation Representations from Depth for RoboticsarXiv:2601.18923v2 Announce Type: replace Abstract: Depth sensors are widely deployed across robotic platforms, and advances in fast, high-fidelity depth simulation have enabled robotic policies train→12 Oct 2026Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression TargetarXiv:2610.12830v1 Announce Type: new Abstract: Reasoning post-training draws on offline demonstrations and policy-generated rollouts, yet conventional supervised fine-tuning (SFT) followed by reinfor→12 Oct 2026Continually Post-training Small Models via Synthetic Self-distillationarXiv:2610.13113v1 Announce Type: cross Abstract: Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. Whil→12 Oct 2026Byzantine-Resilient Federated Large Language Model via Hypergraph Message PassingarXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is→12 Oct 2026Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational InsightsarXiv:2610.12527v1 Announce Type: new Abstract: Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net sm→12 Oct 2026Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries RevealarXiv:2505.15738v3 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted e→12 Oct 2026AI Models Can Provably Hide Arbitrary CapabilitiesarXiv:2610.13928v1 Announce Type: new Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilit→12 Oct 202610 Years of the SRE book: Announcing the second edition of 'Site Reliability Engineering”A decade ago, Google released Site Reliability Engineering: How Google Runs Production Systems with O'Reilly Media. What began as a collection of our practices for managing large-scale infrastructure
TechniqueMultimodal8 recent entries12 Oct 2026Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASRarXiv:2610.13432v1 Announce Type: cross Abstract: Earnings call transcription presents a realistic continual learning scenario where Automatic Speech Recognition (ASR) systems are updated with new rec→12 Oct 2026Decision 3.0: open, multimodal decision models from 0.6B to 27B. Ranks #1 on both Jev Decision Index boardsWith the vLLM Semantic Router team we released Decision 3.0 (d3), our new SOTA decision model family ranging from 0.6B to 27B, Apache-2.0, all reading text, images and video. How it works - Built on Q→12 Oct 2026DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language ModelsarXiv:2603.18048v3 Announce Type: replace Abstract: Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether →12 Oct 2026Continually Post-training Small Models via Synthetic Self-distillationarXiv:2610.13113v1 Announce Type: cross Abstract: Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. Whil→12 Oct 2026Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries RevealarXiv:2505.15738v3 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted e→12 Oct 2026AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMsarXiv:2610.13600v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) achieve strong performance on speech-text tasks, but standard audio encoders produce hundreds of tokens for even s→12 Oct 2026AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum LearningarXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks re→12 Oct 2026Acoustic Biomarkers for Alzheimer's Disease Detection from Spontaneous SpeecharXiv:2610.12500v1 Announce Type: cross Abstract: Alzheimer's disease (AD) remains a major public health challenge, and early identification is crucial for timely intervention and care planning. Recen
TechniqueSafety8 recent entries12 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 2026AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk EvaluationarXiv:2603.07427v3 Announce Type: replace Abstract: As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costl→12 Oct 2026Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMsarXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d→12 Oct 2026APEX-Harm: Evaluating Agent Safety in Shared Professional WorkspacesarXiv:2610.13623v1 Announce Type: cross Abstract: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and busine→12 Oct 2026Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with HumansarXiv:2610.13303v1 Announce Type: cross Abstract: LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-→12 Oct 2026ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring ScenariosarXiv:2510.10998v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hir→12 Oct 2026A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPOarXiv:2610.13669v1 Announce Type: new Abstract: Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection becau→12 Oct 2026A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety AssurancearXiv:2610.13479v1 Announce Type: new Abstract: Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase s