TechniqueRLHF / Alignment8 recent entries15 Oct 2026Aligning Faithfulness for Theory-Scale AutoformalizationarXiv:2610.18498v1 Announce Type: cross Abstract: Autoformalization (AF) requires more than compilation: formal statements must preserve the meaning of their informal sources, a property known as fait→15 Oct 2026AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned GenerationarXiv:2610.14697v1 Announce Type: cross Abstract: Speech-conditioned generation maps speech signals to target audio outputs. Prior end-to-end speech-conditioned generative models achieve high fidelity
TechniqueRAG8 recent entries15 Oct 2026Evidence-Anchored Overdose Death Prediction from Death Investigation ReportsarXiv:2610.19556v1 Announce Type: new Abstract: Confirmation of overdose deaths in the United States is often delayed due to the complexities of certifying drug-involved deaths. Death investigation re→15 Oct 2026Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAGarXiv:2509.21193v2 Announce Type: replace Abstract: Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieva→15 Oct 2026EGCForest: Structured Agent Memory Organization for Enterprise Group ChatsarXiv:2610.19836v1 Announce Type: new Abstract: Enterprise group chats record project progress, decisions, task ownership, and other organizational information valuable to enterprise agents. Reliable →15 Oct 2026DTScribe: Generating Models for Digital Twin Reporting using Local Large Language ModelsarXiv:2610.18635v1 Announce Type: cross Abstract: The development of a digital twin brings together many stakeholders and technical components. We have previously investigated the reporting of the con→15 Oct 2026DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA GatesarXiv:2610.19830v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach listings must pass the diverse CAPTC→15 Oct 2026CoverSynth: Coverage-Guided Generation of Retrieval Evaluation SetsarXiv:2610.15409v1 Announce Type: new Abstract: Enterprise agents need retrieval evaluation sets that expose domain-specific failures and guide developers towards efficient deployment tradeoffs. Neith→15 Oct 2026AutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RANarXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Netw→15 Oct 2026Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-TrainingarXiv:2610.19479v1 Announce Type: new Abstract: Sim-and-real co-training is an effective way to scale robot learning by augmenting limited real-world demonstrations with simulation data. However, exis
TechniqueAgents8 recent entries15 Oct 2026AdaRSI: On-Demand Recursive Self-Improvement for Embodied AgentsarXiv:2610.20474v1 Announce Type: new Abstract: Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, b→15 Oct 2026Adaptive-Group Process Rewards for GUI AgentsarXiv:2610.17710v1 Announce Type: new Abstract: Training graphical user interface (GUI) agents with reinforcement learning suffers from sparse outcome rewards, leading to inefficient learning. Process→15 Oct 2026ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition GapsarXiv:2610.20532v1 Announce Type: cross Abstract: A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no→15 Oct 2026ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-EvolutionarXiv:2610.18355v2 Announce Type: new Abstract: We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embod→15 Oct 2026A Global View of How LLMs Value Human TimearXiv:2610.18515v2 Announce Type: cross Abstract: Large language models (LLMs) increasingly act as personal assistants; however, little is known about how they capture national-level preferences on a →15 Oct 2026A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software EvolutionarXiv:2610.15765v1 Announce Type: cross Abstract: Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designe→15 Oct 2026A Counterfactual Graph Approach to Oppositional Narrative AnalysisarXiv:2603.06135v3 Announce Type: replace-cross Abstract: Distinguishing legitimate critical speech from coordinated conspiracy narratives is a pressing challenge for the integrity of the online infor→15 Oct 20265/5 Across the board, results show the business impact and differentiation of sovereign specialized intelligence, and the opportunity for co…5/5 Across the board, results show the business impact and differentiation of sovereign specialized intelligence, and the opportunity for companies to reach AI independence. Thanks to @nvidia, @Gong_i
TechniqueFine-tuning8 recent entries15 Oct 2026CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation ObjectivesarXiv:2610.16876v1 Announce Type: new Abstract: Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresen→15 Oct 2026Beyond Successful Play: Diagnosing Opponent Modeling in Large Language ModelsarXiv:2610.17310v1 Announce Type: new Abstract: Language-model agents are expected to adapt to others whose behavior changes through interaction. Yet adaptation may rely on learned behavioral patterns→15 Oct 2026Beyond Corrected Actions: Training LLM Agents on Textual CritiquesarXiv:2610.19367v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequ→15 Oct 2026AutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RANarXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Netw→15 Oct 2026AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric ConstraintsarXiv:2512.16245v2 Announce Type: replace Abstract: Merging large language models (LLMs) is a practical way to compose capabilities from multiple fine-tuned checkpoints without retraining. Yet standar→15 Oct 2026AdaRSI: On-Demand Recursive Self-Improvement for Embodied AgentsarXiv:2610.20474v1 Announce Type: new Abstract: Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, b→15 Oct 2026AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian ComputationarXiv:2604.03925v2 Announce Type: replace Abstract: Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a manne→15 Oct 2026Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-TrainingarXiv:2610.19479v1 Announce Type: new Abstract: Sim-and-real co-training is an effective way to scale robot learning by augmenting limited real-world demonstrations with simulation data. However, exis
TechniqueMultimodal8 recent entries15 Oct 2026Atomic-WAM: Execution-Grounded Atomic-Motion Reasoning for World Action ModelsarXiv:2610.20157v1 Announce Type: new Abstract: World Action Models (WAMs) typically adapt video foundation models to robotic control through joint video and action prediction. However, task-level ins→15 Oct 2026Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-CalibrationarXiv:2610.14542v1 Announce Type: new Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has re→15 Oct 2026Are Benchmarks Reliable? Toward Structural Diagnosis via Item-Level Capability BoundariesarXiv:2609.33196v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) relies heavily on benchmark scores, yet aggregate metrics can obscure whether individual items serve their i→15 Oct 2026AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned PrefixesarXiv:2610.14487v1 Announce Type: new Abstract: Generative recommendation models based on autoregressive decoding have been adopted as alternatives to classical ranking-based systems. While their mode→15 Oct 2026AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned GenerationarXiv:2610.14697v1 Announce Type: cross Abstract: Speech-conditioned generation maps speech signals to target audio outputs. Prior end-to-end speech-conditioned generative models achieve high fidelity→15 Oct 2026AdaRSI: On-Demand Recursive Self-Improvement for Embodied AgentsarXiv:2610.20474v1 Announce Type: new Abstract: Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, b→15 Oct 2026ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial NavigationarXiv:2610.15956v1 Announce Type: new Abstract: Vision-language-action models for embodied navigation typically rely on RGB observations, limiting their applicability in lights-out industrial environm→15 Oct 2026ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition GapsarXiv:2610.20532v1 Announce Type: cross Abstract: A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no
TechniqueSafety8 recent entries15 Oct 2026Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg EquilibriaarXiv:2511.17937v2 Announce Type: replace Abstract: Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in→15 Oct 2026AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned GenerationarXiv:2610.14697v1 Announce Type: cross Abstract: Speech-conditioned generation maps speech signals to target audio outputs. Prior end-to-end speech-conditioned generative models achieve high fidelity→15 Oct 2026AI-Driven, Timing-Aware Power OptimizationarXiv:2610.18890v1 Announce Type: cross Abstract: Post-route power recovery changes cell choices under tightly coupled timing, electrical and physical constraints, and the value of each change depends→15 Oct 2026AgentStripes: An Evidence-Graded Maturity Model for AI AgentsarXiv:2610.18603v1 Announce Type: new Abstract: Benchmarks report what an Artificial Intelligence (AI) agent can do on a task suite, but not whether one released version has been engineered with the c→15 Oct 2026Agent-Environment Alignment via Automated Interface GenerationarXiv:2505.21055v2 Announce Type: replace Abstract: Large language model (LLM) agents have shown impressive reasoning capabilities in interactive decision-making tasks. These agents interact with envi→15 Oct 2026AegisVox: Factorized Privacy and Clinical Preservation for Long-Form SpeecharXiv:2610.14643v1 Announce Type: new Abstract: Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and speaker roles can also carry useful clinical e→15 Oct 2026ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition GapsarXiv:2610.20532v1 Announce Type: cross Abstract: A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no→15 Oct 2026A^3PreCore: Robust Rigid Registration for Native FLAIR-Space Brain-Mask TransferarXiv:2610.20561v1 Announce Type: new Abstract: Reliable brain-mask transfer into native fluid-attenuated inversion recovery (FLAIR) space can fail when T1-to-FLAIR rigid registration is unstable. We