TechniqueRLHF / Alignment8 recent entries16 Oct 2026Memorilla: Latent Semantic Memory for LLMsarXiv:2610.21375v1 Announce Type: cross Abstract: Memory enables large language models (LLMs) to use information beyond their parameters, such as past user conversations, long documents, or an agent's→16 Oct 2026KnowGPO: Knowledge-Grouped Policy Optimization for Search AgentsarXiv:2610.22331v1 Announce Type: new Abstract: Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions →
TechniqueRAG8 recent entries16 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 2026Enhancing Knowledge Density via Hierarchical Context Pruning for Retrieval-Augmented Repository-Level Code CompletionarXiv:2508.10068v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has advanced repository-level code completion by retrieving external code snippets, API documentation, or→16 Oct 2026DocPilot: Interactive Agent Orchestration and Training for Long Visual Document UnderstandingarXiv:2610.21327v1 Announce Type: new Abstract: Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document conte→16 Oct 2026Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for AgentsarXiv:2610.21424v1 Announce Type: new Abstract: Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Repres→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 2026CARA: Causally Guided Retrieval Agent for Question AnsweringarXiv:2610.22017v1 Announce Type: new Abstract: Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merel→16 Oct 2026Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAGarXiv:2610.21184v1 Announce Type: new Abstract: Multi-hop retrieval-augmented generation (RAG) requires an agent to retrieve evidence for a sequence of dependent sub-questions. When a wrong answer lac→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 2026Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for AgentsarXiv:2610.21424v1 Announce Type: new Abstract: Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Repres→16 Oct 2026DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational AgentsarXiv:2610.21561v1 Announce Type: cross Abstract: Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has r→16 Oct 2026CertEx: Exact Visual Retrieval at Scale by Certified ExclusionarXiv:2610.21325v1 Announce Type: new Abstract: Exact k-nearest-neighbor (kNN) search over image descriptors and embeddings underlies visual retrieval, near-duplicate detection, the evaluation of lear→16 Oct 2026CARA: Causally Guided Retrieval Agent for Question AnsweringarXiv:2610.22017v1 Announce Type: new Abstract: Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merel→16 Oct 2026Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAGarXiv:2610.21184v1 Announce Type: new Abstract: Multi-hop retrieval-augmented generation (RAG) requires an agent to retrieve evidence for a sequence of dependent sub-questions. When a wrong answer lac→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 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 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
TechniqueFine-tuning8 recent entries16 Oct 2026Stabilizing the Modality Gap: Null-Space Projected Continual Learning for Vision-Language ModelsarXiv:2507.19839v2 Announce Type: replace-cross Abstract: The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared repre→16 Oct 2026RAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub DataarXiv:2510.08667v3 Announce Type: replace-cross Abstract: Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA t→16 Oct 2026QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence FilteringarXiv:2610.21512v1 Announce Type: new Abstract: DeepSearch agents achieve strong performance on complex information-seeking tasks through iterative search and reasoning. However, they often issue inte→16 Oct 2026Memory as Weights: Internalizing Long-Term History for Streaming VideosarXiv:2610.22070v1 Announce Type: cross Abstract: Streaming vision-language models (VLMs) must continuously integrate information from the past while remaining responsive to current observations and u→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 2026Knowledge That Is Linear Before Fine-Tuning Generalizes After ItarXiv:2610.22300v1 Announce Type: cross Abstract: Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond thei→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 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 2026Loud and Clear: Making Visual Evidence Count in Multimodal Document RAGarXiv:2610.21318v1 Announce Type: cross Abstract: Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model →16 Oct 2026Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text MatchingarXiv:2610.21937v1 Announce Type: new Abstract: Vision--language pre-training has enabled substantial progress in image--text retrieval and zero-shot recognition by learning transferable cross-modal r→16 Oct 2026Fast-VLA: You Only Think Once for Robot ManipulationarXiv:2610.21389v1 Announce Type: new Abstract: Vision-language-action (VLA) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whene→16 Oct 2026EMO: A Closed-Loop Test-Time Computation Framework via Alternating Context Optimization and Logits SteeringarXiv:2610.22160v1 Announce Type: cross Abstract: Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate contro→16 Oct 2026DocPilot: Interactive Agent Orchestration and Training for Long Visual Document UnderstandingarXiv:2610.21327v1 Announce Type: new Abstract: Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document conte→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 2026CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for ClusteringarXiv:2610.21805v1 Announce Type: new Abstract: Multimodal objects can require different partitions under different instructions, as when products in an e-commerce catalog are grouped by color, materi→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
TechniqueSafety8 recent entries16 Oct 2026Language Is a Security Surface for Agent GuardsarXiv:2610.22244v1 Announce Type: cross Abstract: Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users writ→16 Oct 2026KnowGPO: Knowledge-Grouped Policy Optimization for Search AgentsarXiv:2610.22331v1 Announce Type: new Abstract: Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions →16 Oct 2026How Do LLM-Generated Texts Impact Term-Based Retrieval Models?arXiv:2508.17715v2 Announce Type: replace-cross Abstract: As more content generated by large language models (LLMs) floods into the Internet, information retrieval (IR) systems now face the challenge →16 Oct 2026EMO: A Closed-Loop Test-Time Computation Framework via Alternating Context Optimization and Logits SteeringarXiv:2610.22160v1 Announce Type: cross Abstract: Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate contro→16 Oct 2026DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational AgentsarXiv:2610.21561v1 Announce Type: cross Abstract: Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has r→16 Oct 2026DemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from DemonstrationarXiv:2610.22020v1 Announce Type: cross Abstract: Learning from demonstration is an effective strategy for endowing robots with manipulation capabilities but requires training on datasets comprised of→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 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