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 entries16 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 2026LLM-as-an-Investigator: Evidence-First Agentic Reasoning for Robust Interactive Problem DiagnosisarXiv:2606.13220v2 Announce Type: replace Abstract: Large language models (LLMs) are used for technical troubleshooting, where problem descriptions are often incomplete and multiple causes can explain→16 Oct 2026Learning from Interaction Experience via Localized Context DistillationarXiv:2610.21427v1 Announce Type: new Abstract: Learning from interaction experience is essential for enabling large language models to continually improve during deployment. Context distillation offe→16 Oct 2026Language Models Share a Readout Bottleneck in Working MemoryarXiv:2610.21176v1 Announce Type: cross Abstract: Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and error→16 Oct 2026Jev-as-a-Judge for RAG Claim Verification: Confidence-Gated Cascading Between a Non-Generative Verifier and a Frontier LLMarXiv:2610.20634v1 Announce Type: new Abstract: Retrieval-augmented generation asks one question at volume: does this evidence support this claim? The answer is one bit, yet most pipelines obtain it f→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→16 Oct 2026Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial EnvironmentsarXiv:2602.16653v4 Announce Type: replace Abstract: Skills are getting increasingly used in recent agentic frameworks, performing robustly with proprietary LLMs. Yet, their effectiveness for small and
TechniqueAgents8 recent entries16 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 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 2026Agentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference ElicitationarXiv:2610.21938v1 Announce Type: cross Abstract: An agent that learns a user's preferences from their choices faces a cold start problem: before any choices are observed, it must rely solely on a pri→16 Oct 2026Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial EnvironmentsarXiv:2602.16653v4 Announce Type: replace Abstract: Skills are getting increasingly used in recent agentic frameworks, performing robustly with proprietary LLMs. Yet, their effectiveness for small and→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→16 Oct 2026A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question AnsweringarXiv:2610.20809v1 Announce Type: new Abstract: A self-improving agent has to decide which new skills to keep, and in practice it keeps whatever earns a high reward, convinces a judge model, or compre→16 Oct 2026A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent SystemsarXiv:2610.21243v1 Announce Type: cross Abstract: Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in scalability, adaptability, and collective perform
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 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 2026Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language ModelsarXiv:2610.20679v1 Announce Type: new Abstract: Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does not→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 2026BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM PartitionarXiv:2610.21565v1 Announce Type: cross Abstract: On-device deployment of large language models (LLMs) is increasingly adopted due to latency and privacy requirements, but exposes proprietary models t→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 2026FastVLA: Task-Conditioned and Temporally Adaptive Visual Token Compression for Efficient Vision-Language-Action ModelsarXiv:2610.22146v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models present a promising paradigm for general-purpose robot manipulation, but closed-loop deployment is often limited by →16 Oct 2026Decoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal AlignmentarXiv:2610.22049v1 Announce Type: cross Abstract: Reconstructing what a person perceives from their brain activity is a stringent test of whether neural recordings carry meaningful information. Natura→16 Oct 2026Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language ModelsarXiv:2610.20679v1 Announce Type: new Abstract: Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does not→16 Oct 2026Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time ReasoningarXiv:2610.20836v1 Announce Type: new Abstract: Evaluator-guided reasoning presents a local control problem at every step: trust the current answer, return a fallback, or spend more inference. We form→16 Oct 2026Change the Number, Change the Answer: Assessing Rating Scale Sensitivity in LLM-Based Text ScoringarXiv:2610.22187v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in computational social science to assign scalar scores to social and psychological constructs. How→16 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 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
TechniqueSafety8 recent entries16 Oct 2026CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM CascadesarXiv:2610.20668v1 Announce Type: cross Abstract: We introduce CascadeLedger, a counterfactual execution-audit framework for budgeted language-model cascades. The protocol enforces call-before-read se→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 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 2026Asynchrony Is Nearly Free for Evolution Strategies on Long-Horizon LLM Agentic TasksarXiv:2610.04196v2 Announce Type: replace Abstract: Synchronous policy updates can limit the efficiency of post-training for long-horizon LLM agents. When trajectories span multiple interaction turns,→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→16 Oct 2026AI Alignment From Social Choice PerspectivesarXiv:2606.21550v2 Announce Type: replace Abstract: Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgme→16 Oct 2026Adaptive Duration Model for Text Speech AlignmentarXiv:2507.22612v3 Announce Type: replace-cross Abstract: Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention m