TechniqueRLHF / Alignment8 recent entries2 Oct 2026Measuring Iterative Temporal Reasoning with Time PuzzlesarXiv:2601.07148v4 Announce Type: replace-cross Abstract: Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchm→2 Oct 2026Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent CollaborationarXiv:2610.02036v1 Announce Type: new Abstract: AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared st
TechniqueRAG8 recent entries4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl→4 Oct 2026Synthesis: Arxiv-Cs-AiAuto-generated synthesis of 29846 entries about arxiv-cs-ai→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→6 Oct 2026InvestigationWorlds: An Agentic Environment for Legal InvestigationarXiv:2610.04129v1 Announce Type: cross Abstract: We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summ→9 Oct 2026When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination DetectionarXiv:2610.10971v1 Announce Type: cross Abstract: Large language models are increasingly used in legal research and drafting, but they can still produce claims that sound convincing without being supp→12 Oct 2026Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge GrapharXiv:2610.13695v1 Announce Type: new Abstract: Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-→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 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 entries9 Oct 2026Sources: top execs at Anthropic, OpenAI, and others are gaming out scenarios for a public and political revolt following a catastrophic AI event (Maria Curi/Axios)Maria Curi / Axios: Sources: top execs at Anthropic, OpenAI, and others are gaming out scenarios for a public and political revolt following a catastrophic AI event — - The first example of significan→9 Oct 2026LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World ModelsarXiv:2610.11253v1 Announce Type: new Abstract: Large language model agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with →9 Oct 2026Claude Malhuret Was Right about Trump. On Friday, at Trump's direction, the US Treasury issued a license waving Russian diesel back onto the…Claude Malhuret Was Right about Trump. On Friday, at Trump's direction, the US Treasury issued a license waving Russian diesel back onto the world market, days after Russia killed dozens of Ukrainians→11 Oct 2026Qwen 3.8 27B Q5 vs Qwen 3.8 Next Q3_S for document analysisI have an app that processes ~500 different documents every day. An agent analyzes them, sorts them, tags them, extracts various legal nuances, creates descriptions, etc. So far I've been using Qwen 3→12 Oct 2026Zai just debuted a legal specific model: GLM Legal, and it is the new #1 open-weight model on Harvey’s Legal Agent Benchmark and LegalBench.Zai recently launched a domain‑specific language model called **GLM Legal**. According to a tweet posted at 4:13 PM on Oct 12, 2026, GLM Legal became the leading open‑weight model on both **Harvey’s L→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 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 →13 Oct 2026Weird blog post from OrcaRouterI came across this blog post from OrcaRouter: https://www.orcarouter.ai/blog/qwen-3-8-next-vs-qwen-3-8 Not only is the blog post nonsensical in some parts, it's also completely without any value. It b
TechniqueFine-tuning8 recent entries4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→5 Oct 2026Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM SignalsarXiv:2610.03112v1 Announce Type: new Abstract: Matching candidates to vacancies is central to recruitment, and a recruiter needs to see why a candidate fits, not only a single opaque relevance score.→8 Oct 2026Is Word Error Rate Enough? Rethinking Privacy Evaluation in Speech with Entity-Aware MetricsarXiv:2610.08831v1 Announce Type: cross Abstract: As the use of smart devices continues to increase, their potential to capture sensitive speech content raises growing privacy concerns. It is therefor→9 Oct 2026Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought FaithfulnessarXiv:2610.12361v1 Announce Type: new Abstract: Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence that the decision fo→11 Oct 2026Qwen 3.8 27B Q5 vs Qwen 3.8 Next Q3_S for document analysisI have an app that processes ~500 different documents every day. An agent analyzes them, sorts them, tags them, extracts various legal nuances, creates descriptions, etc. So far I've been using Qwen 3→12 Oct 2026U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation ExtractionarXiv:2610.12742v1 Announce Type: new Abstract: This paper details our submission to KnowledgeGraphEval 2026 Subtask 2 on directed Arabic relation extraction. We explored encoder-based and large langu→12 Oct 2026Static Gradient Attribution Underperforms a Density-Matched Random Mask on Loss-Based Forgetting Within LoRA B-MatrixarXiv:2610.12744v1 Announce Type: new Abstract: Parameter-efficient continual learning updates a restricted subset of adapter parameters to incorporate sequential tasks while limiting catastrophic for
TechniqueMultimodal8 recent entries24 Sept 2026Groundbench: Multi-Resolution Polygon Grounding Exposes the Geometry Gap in Vision-Language ModelsarXiv:2609.27821v1 Announce Type: new Abstract: Bounding-box scores on RefCOCO-family grounding leave little room to distinguish frontier vision-language systems, yet boxes discard object shape. We in→27 Sept 2026Wiki Lint Report — 2026-09-27Automated lint: 17 errors, 59669 warnings, 3 info→29 Sept 2026The Text Beside the Image: Detection, Utility and Leakage for Trustworthy Multimodal Medical Data and BeyondarXiv:2609.33280v1 Announce Type: cross Abstract: Medical images are released with the reports that describe them, and protecting the image does not protect the report. This paper measures the text co→4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl→4 Oct 2026Synthesis: Arxiv-Cs-AiAuto-generated synthesis of 29846 entries about arxiv-cs-ai→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→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 2026Jevjitsu: Or, How We Tried Generalized Classifiers on EverythingClassification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches w
TechniqueSafety8 recent entries5 Oct 2026HakemBench: A Turkish Benchmark of Typed DecisionsarXiv:2610.02293v1 Announce Type: new Abstract: HakemBench is a Turkish benchmark of typed decisions, in which the model under test reads a text, a question and a fixed set of options and returns a pr→6 Oct 2026Causally Fair Generation with Large Language ModelsarXiv:2610.04444v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate, complete, and transform information in settings where their outputs can shape conseque→6 Oct 2026Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning ModelsarXiv:2610.06439v1 Announce Type: new Abstract: What happens when a legal AI model learns to look like a lawyer instead of reasoning like one? We fine tune Qwen3-8B with Group Relative Policy Optimisa→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 2026Jevjitsu: Or, How We Tried Generalized Classifiers on EverythingClassification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches w→8 Oct 2026Is Word Error Rate Enough? Rethinking Privacy Evaluation in Speech with Entity-Aware MetricsarXiv:2610.08831v1 Announce Type: cross Abstract: As the use of smart devices continues to increase, their potential to capture sensitive speech content raises growing privacy concerns. It is therefor→9 Oct 2026Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System InteractionarXiv:2610.10549v1 Announce Type: new Abstract: Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely constrained due to business and leg→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