Knowledge catalogue
arXiv:2511.20718v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks
arXiv:2610.06902v1 Announce Type: new Abstract: Retrieval-augmented generation grounds language models in external context, but for long documents flat top-k retrieval can cluster on a single region a
arXiv:2610.07070v1 Announce Type: new Abstract: Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool calli
arXiv:2610.04687v2 Announce Type: replace Abstract: Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language mode
arXiv:2610.05417v1 Announce Type: new Abstract: Recent works augment Vision-Language Models with geometry features from pretrained 3D models, expecting that the geometric signal will boost spatial rea
arXiv:2505.24033v3 Announce Type: replace-cross Abstract: We investigate whether hidden states from Structured State Space Models (SSMs) can be merged post hoc to support downstream reasoning. Inspire
arXiv: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
arXiv:2610.02472v1 Announce Type: cross Abstract: Personalized LLM assistants must recover sparse evidence from long conversation histories across queries of varying complexity. We introduce APDMem (A
arXiv:2505.21870v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) generally enhances large language models' (LLMs) ability to solve knowledge-intensive tasks. But RAG coul
arXiv:2610.02373v1 Announce Type: cross Abstract: GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that deter
arXiv:2610.02772v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve as general-purpose interfaces to factual knowledge, but their parameters do not automatically reflect
arXiv:2610.02999v1 Announce Type: new Abstract: Omni-modal large language models (OmniLLMs) unify text, images, audio, and video, yet hallucinate when generation relies on the wrong evidence. Existing
arXiv:2610.02819v1 Announce Type: new Abstract: Improving joint audio-visual reasoning in Omni Large Language Models typically incurs substantial data construction and training costs. Our diagnostics
arXiv:2610.03036v1 Announce Type: cross Abstract: We present WebFovea, a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 with a final score of 57.0 out of 100. The challenge
Whenever I feed codebases into local models (Qwen, DeepSeek R1) or API models, the biggest annoyance is prompt pollution: - Lockfiles (`Cargo.lock`, `package-lock.json`) burning 30,000+ tokens for zer
A while ago I asked here how to turn ~5 million court decisions into structured graphs without running an expensive LLM on every document thanks for the advice . I went with the 'small extractor + cla
So this is maybe a niche problem, but at my job I work on a huge Python codebase and every time I change some shared function I'm basically playing roulette. grep tells who mentions it in the code bas
arXiv:2610.00238v1 Announce Type: cross Abstract: Long-term memory agents increasingly rely on it- erative search and reusable experience to answer questions over large personal, factual, or narrative
arXiv:2602.03006v3 Announce Type: replace Abstract: Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active d
arXiv: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
arXiv:2610.02181v1 Announce Type: new Abstract: We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with native
arXiv:2610.00767v1 Announce Type: cross Abstract: Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later train
arXiv:2610.01177v1 Announce Type: cross Abstract: This work presents Diffusion Layer Integrated Gradients (DLIG), a token attribution method for diffusion language models (DLMs) that extends Integrate
arXiv: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
arXiv:2609.34211v2 Announce Type: replace Abstract: In financial fraud detection, rich semantic context can provide important evidence for transaction behavior modeling and fraud reasoning. However, p
arXiv:2609.39139v1 Announce Type: new Abstract: Adaptive RAG uses signals such as confidence, relevance, support, and retrieval quality to decide when to search or correct evidence. In multi-step retr
arXiv:2609.38684v1 Announce Type: new Abstract: Knowledge-intensive language-model systems typically represent external knowledge as text chunks or static graphs, with limited support for concept evol
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
arXiv:2609.39786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based K
arXiv:2609.38923v1 Announce Type: new Abstract: Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with
arXiv: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
arXiv:2609.38266v1 Announce Type: cross Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside t
arXiv:2609.38764v1 Announce Type: new Abstract: Language models are typically pretrained from random initialization. Recent work challenges this convention, showing that a brief warm-up on abstract, a
arXiv:2609.40170v1 Announce Type: new Abstract: MANETs enable flexible infrastructure-less wireless connectivity in dynamic and resource-constrained environments. As modern MANETs exploit multiple fre
arXiv: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
arXiv:2609.39975v1 Announce Type: cross Abstract: This paper presents an overview of the fourteenth edition of the BioASQ challenge, organized in the context of the Conference and Labs of the Evaluati
arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compac
arXiv: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
arXiv:2609.39363v1 Announce Type: cross Abstract: Multi-image understanding requires MLLMs not only to recognise the content of individual images, but also to organise visual evidence distributed acro
arXiv:2609.38809v1 Announce Type: cross Abstract: Large language models deployed as personalized assistants must reason over long, evolving interaction histories. However, in long-term dialogue reason
arXiv:2609.38861v1 Announce Type: new Abstract: Finding a relevant paper is not the same as producing a verifiable answer from it. LitTraceQA requires canonical paper identifiers, exact evidence at th
Hybrid search, reranking, query decomposition, and query expansion are often treated as must-haves for good RAG. We wanted to see how much each actually helped, so we tested them. Same model, same emb
arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested.
arXiv:2609.37993v1 Announce Type: cross Abstract: The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence o
arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by
arXiv:2608.25466v2 Announce Type: replace-cross Abstract: The functional annotation of genes in non-model organisms remains a significant challenge in computational biology, with 20-70% of sequenced g
arXiv:2609.37351v1 Announce Type: cross Abstract: Test-time compute scaling has emerged as a cornerstone of advanced machine reasoning, yet performing iterative deliberation directly within continuous
arXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence i
arXiv:2609.32269v1 Announce Type: cross Abstract: Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for
arXiv:2609.34633v1 Announce Type: new Abstract: Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revi
arXiv:2609.33972v1 Announce Type: cross Abstract: Existing interpretable graph additive models still face limitations in either computational scalability or modeling flexibility. In terms of structura
arXiv:2609.35738v1 Announce Type: cross Abstract: A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information f
arXiv:2609.33759v1 Announce Type: cross Abstract: When a fact changes, how should a language model update the history stored in its key-value (KV) cache? Hiding the old record is cheap, but it may sti
arXiv:2609.32457v1 Announce Type: new Abstract: Transformers process information strictly forward through depth, preventing deeper computation from revisiting and refining earlier representations. To
arXiv:2609.30298v1 Announce Type: new Abstract: Systematic reviews (SR) are essential for evidence-based research, but their screening phase is highly time-consuming and labor-intensive. Large languag
arXiv:2609.30751v1 Announce Type: new Abstract: Pairwise language-model judges can gather evidence through direct comparison, reasoning, or reference-based verification, but no single protocol is best
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