Knowledge catalogue
arXiv:2609.30952v1 Announce Type: cross Abstract: Multi-view video understanding requires integrating spatial and temporal evidence across multiple, often non-overlapping camera streams: tracking enti
arXiv:2609.30838v1 Announce Type: new Abstract: Effective behavioral intervention in chronic disease management requires not a single prescription but a sequence of incremental steps, each grounded in
arXiv:2609.30604v1 Announce Type: cross Abstract: Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, mul
arXiv:2609.28813v1 Announce Type: new Abstract: Cinematography, the craft of visual storytelling through framing, lighting, and camera operation, fundamentally shapes how audiences perceive and emotio
In this episode of The Agent Factory, we explore the reality of building with autonomous agents alongside Ryan Lopopolo, a software engineer at Google Cloud and the person who coined the term agent ha
arXiv:2609.27038v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer. Previous faithfu
arXiv:2609.27373v1 Announce Type: new Abstract: Recurrent language models repeatedly apply shared network blocks to refine latent representations, but standard inference recomputes global attention at
arXiv:2609.28247v1 Announce Type: cross Abstract: Large Language Models (LLMs) introduce an exciting new paradigm for planning and navigation in robotics, but fail on even simple multi-robot tasks as
arXiv:2609.27297v1 Announce Type: new Abstract: Accumulated scientific knowledge advances inquiry when prior findings help researchers choose new questions, design investigations, and interpret result
arXiv:2609.27009v1 Announce Type: new Abstract: Large language models are increasingly applied to high-risk domains such as law, yet complex legal reasoning remains limited by two structural challenge
arXiv:2609.27380v1 Announce Type: new Abstract: Likelihood-based context compression can account for cross-context redundancy through sequential scoring, but this makes compression outcomes sensitive
arXiv:2609.27035v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout i
arXiv:2609.26094v1 Announce Type: new Abstract: Multi-step causal reasoning requires chaining inferences where each step constrains the next. An early error propagates silently, and a correct answer r
arXiv:2609.26086v1 Announce Type: new Abstract: An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop.
arXiv:2505.13994v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy tra
Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the
arXiv:2602.18307v2 Announce Type: replace-cross Abstract: Large language models have achieved striking results in interactive theorem proving, particularly in Lean. However, most benchmarks for LLM-ba
arXiv:2609.22158v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length,
Hi all! After all the jev hype I wanted to try by myself and got qwen3.8 27b to mix-and-match open implementations on top of ninfer, and to be honest I'm quite impressed with the results, latency is n
arXiv:2602.13699v2 Announce Type: replace Abstract: Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evalua
arXiv:2609.20271v1 Announce Type: new Abstract: Reliable and low-latency communication is a fundamental requirement for smart city services and Industry 4.0 applications enabled by NR-V2X networks. Ho
arXiv:2609.19897v1 Announce Type: new Abstract: Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genre
arXiv:2609.18860v1 Announce Type: cross Abstract: When a large vision-language model misclassifies a harmful meme, the failure may reflect missing internal evidence or an inability to route represente
arXiv:2609.18154v1 Announce Type: cross Abstract: We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite the
arXiv:2609.18248v1 Announce Type: cross Abstract: An advanced retrieval-augmented generation pipeline is typically assembled from three or four independently operated systems: an approximate nearest-n
arXiv:2609.18769v1 Announce Type: new Abstract: Correctly answering a question grounded in normative documents often depends on information outside any single passage: whether the retrieved document i
arXiv:2609.18677v1 Announce Type: new Abstract: Speech language models enable richer spoken interactions between humans and machines than cascaded systems, allowing access to paralinguistic informatio
arXiv:2609.18182v1 Announce Type: new Abstract: Real-world agents fundamentally require persistent non-parametric knowledge for dynamic reasoning, i.e., long-term memory and retrieval-augmented genera
arXiv:2609.16912v1 Announce Type: new Abstract: We describe tus-nlp's Lit3R (Retrieve-Relate-Read) system for LitTraceQA, a shared task for literature-grounded question answering that requires systems
arXiv:2609.17416v1 Announce Type: new Abstract: Voice agents built on LLMs follow a rigid listen-think-speak loop that inserts seconds of dead air before every reply. We show that continuous-time cogn
Nice work from Adobe. It's standard practice to store a fixed reference answer for every eval case. When the underlying data changes daily, that stored answer goes stale. Adobe researchers write each
arXiv:2609.17112v1 Announce Type: new Abstract: Large video models have exhibited impressive performance on a wide range of visual question answering tasks, owing to the rise of powerful, pretrained t
arXiv:2609.16233v1 Announce Type: cross Abstract: Vision-language models excel at 2D image understanding but remain limited in 3D spatial reasoning. Progress is hindered by limitations in current benc
arXiv:2609.17419v1 Announce Type: new Abstract: Long-horizon LLM agents must maintain task state across extended sequences of observations, actions, tool calls, and intermediate beliefs. We study thes
arXiv:2609.14178v1 Announce Type: new Abstract: The rapid diffusion of hate speech and misinformation on social networks challenges democratic societies, since direct suppression efforts may deepen po
arXiv: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
arXiv:2609.14739v1 Announce Type: cross Abstract: Large language models are increasingly used in high-stakes domains such as law, where systems must ground their reasoning in retrieved evidence and ab
arXiv:2609.15660v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds a language model's answers on retrieved external knowledge and returns each answer with citations that id
arXiv:2609.13664v1 Announce Type: new Abstract: Knowledge graphs are increasingly distributed across autonomous organizations that share an entity space but own disjoint subsets of relations, forming
arXiv:2609.15234v1 Announce Type: new Abstract: Recently, Large Language Models (LLMs) have gained significant attention due to their strong language understanding and generation capabilities, demonst
arXiv:2609.13808v1 Announce Type: new Abstract: Structured knowledge fact checking aims to determine the truthfulness of natural language claims by reasoning over structured evidence. Recent program-g
arXiv:2609.14066v1 Announce Type: cross Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on complex multimodal reasoning tasks, they remai
arXiv:2609.15695v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains ch
arXiv:2609.14773v1 Announce Type: new Abstract: As LLM conversations grow to hundreds of turns, full-context injection incurs O(N^2) cumulative token costs, while lossy summarization or hard truncatio
arXiv:2609.14412v1 Announce Type: new Abstract: Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmark
arXiv:2609.15932v1 Announce Type: new Abstract: Recurrent GNNs iterate message passing to convergence, and their logical characterizations to date rely on multi-set aggregation, graded (counting) logi
arXiv:2609.14825v1 Announce Type: cross Abstract: Large language models (LLMs) are often deemed unsafe for clinical question answering because of their tendency to hallucinate. Retrieval augmentation,
arXiv: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
arXiv:2609.15964v1 Announce Type: new Abstract: Large language models (LLMs) have been widely adopted for clinical question answering (QA). Current systems can attach citations to their answers, but t
arXiv:2609.12260v1 Announce Type: new Abstract: Large language models (LLMs) can generate biomedical hypotheses, but it remains unclear whether they truly reason from scientific evidence or simply pro
arXiv:2609.12655v1 Announce Type: new Abstract: Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, ex
arXiv:2609.13005v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are inc
arXiv:2609.11243v1 Announce Type: new Abstract: Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses. These
arXiv:2609.11758v1 Announce Type: new Abstract: Allowing large language models (LLMs) to retrieve information from a set of trusted documents can increase reliability and reduce hallucination. However
arXiv:2602.06034v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improv
arXiv:2609.10263v1 Announce Type: new Abstract: Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question.
arXiv:2609.07075v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is commonly evaluated by whether the final answer is correct. That test is insufficient: an answer can match its re
arXiv:2505.13520v2 Announce Type: replace-cross Abstract: Textbook question answering (TQA) is a complex task, requiring the interpretation of complex multimodal context. Although recent advances have
arXiv:2602.05354v3 Announce Type: replace Abstract: Autonomous web agents are increasingly deployed in moderation and policy enforcement, where correct decisions often depend on evidence that is not i
arXiv:2504.18376v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, a