CompanyAnthropic8 recent entries19 May 2026Episodic-Semantic Memory Architecture for Long-Horizon Scientific AgentsarXiv:2605.17625v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scienti→5 Aug 2026Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch AgentarXiv:2608.03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense s
CompanyOpenAI3 recent entries30 Apr 2026Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language ModelsarXiv:2401.00761v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) like ChatGPT are foundational in various applications due to their extensive knowledge from pre-training and fine→19 May 2026Episodic-Semantic Memory Architecture for Long-Horizon Scientific AgentsarXiv:2605.17625v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scienti→22 Sept 2026SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State MachinearXiv:2410.17021v2 Announce Type: replace Abstract: Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. Ho
CompanyGoogle8 recent entries5 Aug 2026Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch AgentarXiv:2608.03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense s→6 Aug 2026The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and LearningarXiv:2608.04285v1 Announce Type: new Abstract: Neurosymbolic AI systems that integrate machine learning and symbolic reasoning are rapidly gaining attention. They complement the data-intensive statis→14 Aug 2026Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning TracesarXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signa→28 Aug 2026AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-CallingarXiv:2608.26623v1 Announce Type: new Abstract: LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely un→15 Sept 2026Before You Poll with LLMs: A Deliberative Diagnostic FrameworkarXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM pers→1 Oct 2026Hierarchical Reasoning ModelarXiv:2506.21734v4 Announce Type: replace Abstract: Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language →1 Oct 2026EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific DiscoveryarXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents →6 Oct 2026VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video ResearcharXiv:2610.04911v1 Announce Type: cross Abstract: Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that releva
CompanyMeta8 recent entries15 Sept 2026Before You Poll with LLMs: A Deliberative Diagnostic FrameworkarXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM pers→1 Oct 2026Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question AnsweringarXiv:2609.38473v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of ret→1 Oct 2026Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic ReasoningarXiv:2609.39437v1 Announce Type: new Abstract: Large language models (LLMs) encode substantial latent geographic knowledge, yet they reason poorly over space and are unreliable when queried from coor→1 Oct 2026Evaluating Whether LLMs Can Reliably Connect the DOTs?arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mis→1 Oct 2026Conformal Factuality Control for Multi-Hop Retrieval-Augmented GenerationarXiv:2609.38222v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated clai→2 Oct 2026HHR: Hierarchical Hash Retrieval for Efficient LLM GenerationarXiv:2610.01230v1 Announce Type: new Abstract: Efficient long-context inference is essential for large language models (LLMs), yet it poses a severe computational bottleneck. Hash-based retrieval off→8 Oct 2026Bridge Routing Heads: Where Multilingual Multi-hop Reasoning Lives in LLMsarXiv:2610.09733v1 Announce Type: new Abstract: Multilingual LLMs answer the same multi-hop reasoning question across languages, but we lack a mechanistic account of whether they share an internal cir→12 Oct 2026Let Large Language Models Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question AnsweringarXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Me
CompanyMistral6 recent entries12 May 2026GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution ShapingarXiv:2603.12275v1 Announce Type: cross Abstract: Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and dige→8 Jun 2026A Four-Condition Diagnostic Protocol for Evidence Utilization in Long-Context and Retrieval-Augmented Language ModelsarXiv:2606.06758v1 Announce Type: new Abstract: Final-answer accuracy, retrieval recall, and citation overlap do not by themselves identify whether a long-context or retrieval-augmented language model→24 Aug 2026DirEAG: Dirichlet Evidence Aggregation for Calibrating Verbalized Confidence in Mathematical ReasoningarXiv:2608.20717v1 Announce Type: new Abstract: Reliable confidence estimation is essential for using large language models in mathematical reasoning, but black-box verbalized confidence is difficult →28 Aug 2026Evaluating Confidence-Gated Retrieval with Matched Trajectory ReplayarXiv:2608.26846v1 Announce Type: cross Abstract: Interactive language-model agents use confidence signals to decide whether to answer immediately, retrieve additional evidence (from memory or externa→15 Sept 2026TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOpsarXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy risk→1 Oct 2026A helps B while B hurts A: directed transfer in instruction-tuning mixturearXiv:2609.39702v1 Announce Type: new Abstract: Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to train on under a fixed budget, and testing one choice
CompanyDeepSeek8 recent entries29 Jun 2026Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMsarXiv:2606.27909v1 Announce Type: cross Abstract: Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden →31 Aug 2026Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question AnsweringarXiv:2608.27925v1 Announce Type: new Abstract: Entity-Memory graph retrieval keeps dialogue turns as verbatim Memory nodes, links repeated mentions through shared Entities, and connects adjacent Memo→3 Sept 2026Trace as State: Reasoning Traces as Conditional States for Long-Context TransformersarXiv:2609.02702v1 Announce Type: new Abstract: Transformers process information causally, but long-context reasoning may depend on task state discovered only later. We formalize this mismatch through→3 Sept 2026Learning to Fuse LLMs with Ontology Rankers for Rare-Disease DiagnosisarXiv:2609.02473v1 Announce Type: new Abstract: Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to matched patient phenotypes. Large language models (LLM→15 Sept 2026Before You Poll with LLMs: A Deliberative Diagnostic FrameworkarXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM pers→1 Oct 2026Evaluating Whether LLMs Can Reliably Connect the DOTs?arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mis→8 Oct 2026EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional MemoryarXiv:2610.10533v1 Announce Type: new Abstract: Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language model→12 Oct 2026Let Large Language Models Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question AnsweringarXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Me
CompanyNVIDIA4 recent entries7 May 2026When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AIarXiv:2605.03213v1 Announce Type: cross Abstract: Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocol→18 Aug 2026The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval BenchmarksarXiv:2608.16096v1 Announce Type: cross Abstract: Enterprises connect language models to their own data through retrieval. The benchmarks that rank multi-hop retrieval systems leave out two facts a bu→21 Aug 2026From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAGarXiv:2608.19535v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieve→15 Sept 2026TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOpsarXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy risk