Knowledge catalogue
arXiv:2509.26574v4 Announce Type: replace Abstract: While large language models (LLMs) with reasoning capabilities are progressing rapidly on high-school math competitions and coding, can they reason
arXiv:2605.06524v2 Announce Type: replace Abstract: Reliable human-machine discrimination is becoming increasingly important as large language models and autonomous agents are deployed in online setti
arXiv:2605.10848v1 Announce Type: cross Abstract: Does a lexical retriever suffice as large language models (LLMs) become more capable in an agentic loop? This question naturally arises when building
arXiv:2605.08703v1 Announce Type: new Abstract: Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-sc
arXiv:2605.08313v1 Announce Type: cross Abstract: Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chai
arXiv:2602.03916v3 Announce Type: replace-cross Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs).
arXiv:2603.00541v2 Announce Type: replace Abstract: Generative foundation models are increasingly scaled in both width and depth, posing significant challenges for stable feature learning and reliable
arXiv:2605.08366v1 Announce Type: new Abstract: We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test W
arXiv:2605.10019v1 Announce Type: cross Abstract: Generative models trained on finite data face a fundamental tension: their score-matching or next-token objective converges to the empirical training
arXiv:2605.08475v1 Announce Type: cross Abstract: Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, ofte
arXiv:2605.09227v1 Announce Type: new Abstract: [Abridged] Using a Large Language Model (LLM) as an automatic rater (LLM-as-a-judge) is cheap but potentially biased: some judges run lenient, others st
Voice artificial intelligence startup Vapi Inc. said today it has raised 50 million in new funding to change the way people talk to computers, experience phone calls and interact with customer support
arXiv:2605.08933v1 Announce Type: new Abstract: Muon orthogonalizes matrix updates, but multi-head attention naturally operates at the level of heads. This granularity mismatch raises the question of
arXiv:2605.09860v1 Announce Type: new Abstract: Long-horizon reasoning requires deciding not only what actions to take, but how deeply to commit before the next observation. We formalize this as commi
arXiv:2605.06869v1 Announce Type: new Abstract: AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no u
arXiv:2605.06607v2 Announce Type: replace-cross Abstract: Recent LLM-based agents have closed substantial portions of the scientific discovery loop in software-only machine-learning research, in chemi
arXiv:2601.15050v4 Announce Type: replace Abstract: Current evaluation methods for Retrieval Augmented Generation (RAG) suffer from extit{factual myopia}: they relentlessly emphasize factual accuracy
arXiv:2605.06890v1 Announce Type: new Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagn
arXiv:2605.08057v1 Announce Type: cross Abstract: While recent advancements in inference-time learning have improved LLM reasoning on Text-to-SQL tasks, current solutions still struggle to perform wel
arXiv:2512.09629v2 Announce Type: replace Abstract: We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language a
Fine-tuning on your proprietary data is the highest leverage thing you can do. Prompts get copied overnight. A model trained on your data, your evals, your edge cases is a strong moat. OpenAI is windi
arXiv:2605.07209v1 Announce Type: cross Abstract: We introduce a proxy-analyzer framework for detecting hallucinations in large language models. Instead of looking inside the generating model, our sys
arXiv:2605.06832v1 Announce Type: cross Abstract: Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assis
arXiv:2603.24946v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on
One of the most important properties of LLMs that we take for granted is that newer, bigger models are just better at everything. The AI Labs are pouring effort into economically valuable fields like
arXiv:2512.14018v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance cod
arXiv:2602.21858v4 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confin
arXiv:2602.15189v2 Announce Type: replace-cross Abstract: Producing output that conforms to a specified JSON schema underlies tool use, structured extraction, and knowledge base construction in modern
arXiv:2605.06822v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationa
arXiv:2605.07001v1 Announce Type: cross Abstract: Architectural code smells erode software maintainability and are costly to repair manually, yet unlike localized bugs, they require cross-module reaso
arXiv:2605.07870v1 Announce Type: cross Abstract: We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mea
arXiv:2601.23251v2 Announce Type: replace Abstract: State-of-the-art vision-language models (VLMs) score impressively on video benchmarks yet stumble on basic visual reasoning tasks involving spatial
arXiv:2605.07748v1 Announce Type: new Abstract: Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos. A natural next st
arXiv:2605.06729v1 Announce Type: cross Abstract: We present the EDelta-MHC-Geo Transformer, a novel architecture that unifies Manifold-Constrained Hyper-Connections (mHC), Deep Delta Learning (DDL),
arXiv:2605.06707v1 Announce Type: cross Abstract: This paper presents an eight-week observational comparison of 68 single-file HTML generations collected across 17 public experiments in the 'HTML AI B
arXiv:2602.04774v2 Announce Type: replace-cross Abstract: Setting the learning rate (LR) for a deep learning model is a critical part of successful training. Choosing LRs is often done empirically wit
arXiv:2510.01290v2 Announce Type: replace Abstract: The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (
TIL: Using LLM in the shebang line of a script Kim_Bruning on Hacker News: But seriously, you can put a shebang on an english text file now (if you're sufficiently brave) [...] This inspired me to loo
This is just mindblowing stuff! I couldn't resist replicating this workflow to generate 3D biological structures. In a few minutes, I designed an artifact specifically built to generate these for any
Take Mythos seriously, but don’t panic. Here are the facts: • Mythos is a real threat. And it can really help with finding bugs (as @mozilla’s new report documents well). • It’s not unique; similar vu
arXiv:2605.04083v1 Announce Type: new Abstract: Much of the focus in RL today is on evaluation design: building meaningful evals that serve simultaneously as benchmarks and as well-defined reward sign
arXiv:2605.04556v1 Announce Type: cross Abstract: The Massive Sound Embedding Benchmark (MSEB) has emerged as a standard for evaluating the functional breadth of audio models. While initial baselines
arXiv:2605.04085v1 Announce Type: cross Abstract: Objectives: Large language models (LLMs) are increasingly used for clinical text summarization, yet structured methods to assess associated patient sa
If Llama 4 didn’t fail, if Microsoft had pulled Sydney after the Roose article, if New Sonnet hadn’t been so good, if Orion hadn’t been so meh, if the leadership change at OpenAI had happened, if a re
arXiv:2605.04261v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and modera
arXiv:2605.04291v1 Announce Type: new Abstract: We present a discrete diffusion-based language model using Glauber dynamics from statistical physics. Our main insight is that instead of trying to trai
arXiv:2605.03675v1 Announce Type: new Abstract: Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over
arXiv:2605.05175v1 Announce Type: cross Abstract: Background: Existing MRI LLM benchmarks rely mainly on review-book multiple-choice questions, where top proprietary models already score highly, limit
arXiv:2605.04208v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive multilingual capabilities for well-resourced languages, yet their performance on low-resource
arXiv:2605.05159v1 Announce Type: new Abstract: We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fin
arXiv:2605.04539v1 Announce Type: new Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference si
arXiv:2605.04897v1 Announce Type: new Abstract: Extraction at ingestion is the wrong primitive for agent memory: content discarded before the query is known cannot be recovered at retrieval time. We p
arXiv:2602.00305v2 Announce Type: replace-cross Abstract: LLM-based vulnerability detectors are increasingly deployed in CI/CD security gating, yet their resilience to evasion under syntax- and compil
arXiv:2605.04426v1 Announce Type: new Abstract: We introduce Telegraph English (TE), a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect. Where
arXiv:2605.03195v1 Announce Type: new Abstract: Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibiliti
arXiv:2605.04107v1 Announce Type: cross Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, n
arXiv:2509.14448v2 Announce Type: replace Abstract: Benchmarks such as SWE-bench and ARC-AGI demonstrate how shared datasets accelerate progress toward artificial general intelligence (AGI). We introd
arXiv:2605.05161v1 Announce Type: new Abstract: Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is funda
arXiv:2605.03998v1 Announce Type: new Abstract: Emergency department triage assigns patients an acuity score that determines treatment priority, and clinical evidence documents persistent gender dispa
arXiv:2605.03387v1 Announce Type: new Abstract: Large language models perform well on high-resource pairs but are less reliable for Japanese-Chinese sentences containing noun-modifying clause construc