TechniqueRLHF / Alignment8 recent entries16 Oct 2026CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM HonestyarXiv:2610.22292v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still ex→16 Oct 2026Bias Control and Injection for Multi-Agent AggregationarXiv:2610.21290v1 Announce Type: new Abstract: Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision s
TechniqueRAG8 recent entries15 Oct 2026ActICL: Post-Training for Agentic Multimodal In-Context LearningarXiv:2610.19475v1 Announce Type: cross Abstract: Multimodal in-context learning (ICL) is an important capability of multimodal large language models (MLLMs). Its performance is closely tied to the de→16 Oct 2026VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long DocumentsarXiv:2610.20964v1 Announce Type: cross Abstract: Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis→16 Oct 2026Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient NotesarXiv:2610.21477v1 Announce Type: new Abstract: Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to fre→16 Oct 2026MemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM AgentsarXiv:2610.21405v1 Announce Type: new Abstract: Long-term memory has become a crucial component of large language model (LLM) agents, with most research focusing on retrieving relevant information acc→16 Oct 2026MeddeX: A Retrieval-Augmented LLaMA-3 System with Gemini Vision for Evidence-Backed Medical Report AnalysisarXiv:2610.20632v1 Announce Type: new Abstract: Modern healthcare generates increasingly complex medical reports that challenge clinical professionals in terms of time and interpretive burden. Manual →16 Oct 2026From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language ModelsarXiv:2610.21165v1 Announce Type: new Abstract: Long-context capability has become essential for large language models (LLMs) to handle complex tasks, yet continuously expanding the context window doe→16 Oct 2026FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination DetectorsarXiv:2610.21483v1 Announce Type: new Abstract: Large language models can produce fluent answers that the supplied context does not support. A compact frozen proxy model can detect such answers by rea→16 Oct 2026Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Batch Processing FrameworkarXiv:2602.05708v2 Announce Type: replace-cross Abstract: Large language models (LLMs) offer a compelling approach to entity matching (EM) in label-scarce settings, yet their matching quality is sensi
TechniqueAgents8 recent entries16 Oct 2026ARGUS: An Agenda-Driven Framework for Reliable User SimulationarXiv:2610.21346v1 Announce Type: new Abstract: High-fidelity user simulators are essential for evaluating and training agents in interactive environments. However, current LLM-based simulators strugg→16 Oct 2026Anvil: Scaling Embodied Spatial Intelligence through Knowledge RecirculationarXiv:2610.21882v1 Announce Type: cross Abstract: Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this kno→16 Oct 2026Another in-depth review from @zacbowden for @WindowsCentral: https://windowscentral.com/hardware/nvidia/rtx-spark-review-benchmarks-2026The tweet from @NousResearch links to a Windows Central article written by Zac Bowden that provides an in‑depth review and benchmark analysis of Nvidia’s RTX Spark. Posted on Oct 16, 2026, the review →16 Oct 2026AlphaDiana: A Measurement System for Agents in Verifiable Reasoning TasksarXiv:2610.20675v1 Announce Type: new Abstract: Agents pair reasoning models with harnesses that organize model calls, execute tools, load skill instructions, and retain history in memory. Understandi→16 Oct 2026All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory AgentsarXiv:2610.21147v1 Announce Type: new Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and leng→16 Oct 2026AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction PerturbationsarXiv:2610.21624v1 Announce Type: new Abstract: Real-world tasks are often complex and noisy, posing substantial challenges for LLM agents. Yet existing evaluations lack a systematic framework for joi→16 Oct 2026AgentEval: Evidence-Bounded Assessment of Stateful AgentsarXiv:2610.21177v1 Announce Type: new Abstract: Task completion alone does not determine whether a stateful agent satisfied its obligations, and a recorded judgment does not guarantee that its support→16 Oct 2026A team of Gemini 4 Argon agents beats MinecraftarXiv:2610.22319v1 Announce Type: new Abstract: We placed four Gemini 4 Argon agents in a sandboxed Minecraft survival world and gave them one goal: defeat the Ender Dragon. Each agent controlled a pl
TechniqueFine-tuning8 recent entries16 Oct 2026EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open WorldsarXiv:2610.20786v1 Announce Type: new Abstract: Multi-modal agents have made significant progress in interacting with open worlds. However, their ability to self-evolve remains limited. Supervised fin→16 Oct 2026Evo-DexBench: Benchmarking Generalization across Related Tasks for Dexterous ManipulationarXiv:2610.21180v1 Announce Type: new Abstract: General-purpose dexterous manipulation requires policies to transfer knowledge from related tasks to new tasks with only a few target demonstrations. Ex→16 Oct 2026EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric AlignmentarXiv:2610.22186v1 Announce Type: cross Abstract: Recent advances in Omni Language Models (OLMs) provide a unified solution for audiovisual video captioning. Nevertheless, existing approaches predomin→16 Oct 2026Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent AdaptationarXiv:2610.20652v1 Announce Type: new Abstract: Always-on virtual assistants increasingly personalize on-device to new user-specific commands via few-shot fine-tuning (e.g., LoRA), but this adaptation→16 Oct 2026DeciCAD: Harness-Grounded Learning of Action Policies for CAD AgentsarXiv:2610.21755v1 Announce Type: new Abstract: Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this ope→16 Oct 2026CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM HonestyarXiv:2610.22292v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still ex→16 Oct 2026Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative GenerationarXiv:2610.21468v1 Announce Type: cross Abstract: Every story has two orders: the order in which its events happen and the order in which they are told. A story is nonlinear when the two differ. We in→16 Oct 2026All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory AgentsarXiv:2610.21147v1 Announce Type: new Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and leng
TechniqueMultimodal8 recent entries16 Oct 2026Beyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial ImagesarXiv:2610.21760v1 Announce Type: new Abstract: As image generation models become increasingly capable of producing highly realistic content, traditional forensic techniques are struggling to keep up.→16 Oct 2026Beyond Downstream QA: Rethinking How We Evaluate Agent MemoryarXiv:2610.22209v1 Announce Type: cross Abstract: Agent memory benchmarks evaluate whether an agent's responses reflect correct knowledge, measuring downstream question-answering accuracy as a proxy f→16 Oct 2026BD-HazardVLM: Probing Vision-Language Models for Latent Defensive-Driving Hazards in Bangladesh Road ScenesarXiv:2610.20627v1 Announce Type: new Abstract: Vision-language models are increasingly used for driving-scene understanding, yet their defensive reasoning under weakly structured Global South traffic→16 Oct 2026Audio-Visual Dog Identification and Tracking in Real-World VideosarXiv:2610.21011v1 Announce Type: new Abstract: Identifying individual dogs from barks in real-world videos remains challenging and largely unexplored. Solving this problem would enable long-term beha→16 Oct 2026APRiL: An Open-ended Benchmark for Chinese Social Awareness in Large Language ModelsarXiv:2610.20785v1 Announce Type: new Abstract: Large language models are increasingly used in social interactions, where appropriate responses require recognizing implicit cues, inferring mental stat→16 Oct 2026Anvil: Scaling Embodied Spatial Intelligence through Knowledge RecirculationarXiv:2610.21882v1 Announce Type: cross Abstract: Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this kno→16 Oct 2026AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEOarXiv:2506.03371v2 Announce Type: replace Abstract: Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risk→16 Oct 2026A Multimodal Emotion Recognition System: Integrating Facial Expressions, Body Movement, Speech, and Spoken LanguagearXiv:2412.17907v2 Announce Type: replace-cross Abstract: Psychological evaluation relies on clinicians' observation and interpretation of a patient's emotional expression, which is susceptible to sub
TechniqueSafety8 recent entries16 Oct 2026DeciCAD: Harness-Grounded Learning of Action Policies for CAD AgentsarXiv:2610.21755v1 Announce Type: new Abstract: Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this ope→16 Oct 2026Condition-Contrastive Extrapolation for On-Policy Distillation of Language ModelsarXiv:2610.21195v1 Announce Type: new Abstract: On-policy distillation (OPD) improves a student language model by training on its own generated trajectories with supervision from a stronger teacher. H→16 Oct 2026Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative GenerationarXiv:2610.21468v1 Announce Type: cross Abstract: Every story has two orders: the order in which its events happen and the order in which they are told. A story is nonlinear when the two differ. We in→16 Oct 2026Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation MethodsarXiv:2610.21763v1 Announce Type: new Abstract: Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcrip→16 Oct 2026Bias Control and Injection for Multi-Agent AggregationarXiv:2610.21290v1 Announce Type: new Abstract: Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision s→16 Oct 2026BD-HazardVLM: Probing Vision-Language Models for Latent Defensive-Driving Hazards in Bangladesh Road ScenesarXiv:2610.20627v1 Announce Type: new Abstract: Vision-language models are increasingly used for driving-scene understanding, yet their defensive reasoning under weakly structured Global South traffic→16 Oct 2026All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory AgentsarXiv:2610.21147v1 Announce Type: new Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and leng→16 Oct 2026AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second OpinionsarXiv:2610.22298v1 Announce Type: cross Abstract: Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clini