Knowledge catalogue
arXiv:2511.14584v3 Announce Type: replace-cross Abstract: We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commi
arXiv:2605.27955v1 Announce Type: cross Abstract: Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation synt
arXiv:2605.27401v1 Announce Type: cross Abstract: There is a growing interest in utilizing synthetic populations for a diverse range of applications. At the same time, we are witnessing a tremendous g
arXiv:2605.26747v1 Announce Type: new Abstract: Large Language Models (LLMs) have brought huge improvements to Artificial Intelligence (AI), which can be applied to general-purpose tasks. However, the
arXiv:2605.26179v1 Announce Type: cross Abstract: Density functional theory (DFT) serves as the basis for computational discovery in materials science and chemistry, yet each calculation demands exten
arXiv:2603.03194v2 Announce Type: replace Abstract: Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software en
arXiv:2605.26484v1 Announce Type: new Abstract: Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood.
arXiv:2605.26893v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization,
arXiv:2605.26807v1 Announce Type: cross Abstract: LLMs can now produce full HTML pages, but many of those pages are only superficially correct: they render once, then fail under scroll, hover, click,
arXiv:2605.26947v1 Announce Type: new Abstract: Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt datase
arXiv:2605.26781v1 Announce Type: new Abstract: Advanced Large Multimodal Models (LMMs) have demonstrated impressive performance in K-12 reasoning tasks, exhibiting great promise as intelligent tutors
arXiv:2601.18987v5 Announce Type: replace-cross Abstract: Determining whether a program terminates is a central problem in computer science. Turing's Halting Problem established termination as undecid
arXiv:2605.26343v1 Announce Type: new Abstract: Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recover
arXiv:2506.00250v4 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable performance on a wide range of Natural Language Processing (NLP) benchmarks, often surpassing
arXiv:2603.14864v2 Announce Type: replace Abstract: In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budget management, and bundle deals, where accurately capturing u
arXiv:2603.28730v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervis
arXiv:2605.26346v1 Announce Type: new Abstract: Objective: To describe the design and early clinical evaluation of The Daily Dose (TDD), an LLM-driven, automated clinical summarization and clinical-tr
arXiv:2605.26489v1 Announce Type: new Abstract: Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We ident
arXiv:2605.27154v1 Announce Type: new Abstract: While rule-based reinforcement learning has recently catalyzed explicit reasoning in multimodal models, tactile reasoning remains largely underexplored.
arXiv:2510.17759v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplor
arXiv:2510.22874v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has led to increasingly human-like AI-generated text, raising concerns about content authentic
arXiv:2505.24876v2 Announce Type: replace-cross Abstract: Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understandi
arXiv:2605.25358v1 Announce Type: cross Abstract: AI-associated lexical shifts have been documented mainly in Scientific English. We extend this work to 34 languages in the WMT News Crawl corpus, refi
arXiv:2605.24573v1 Announce Type: new Abstract: Understanding why a spacecraft maneuvers -- rather than simply that it did -- is an increasingly important problem for space domain awareness as Earth o
arXiv:2605.25549v1 Announce Type: cross Abstract: High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production m
arXiv:2510.22143v3 Announce Type: replace Abstract: Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) remain misaligned with real-world dialogue requirements
arXiv:2605.24053v1 Announce Type: new Abstract: Large Language Models (LLMs) are predominantly governed by probabilistic frameworks in which the sum of outcome probabilities is constrained to unity. T
arXiv:2605.26086v1 Announce Type: new Abstract: Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Y
arXiv:2605.25225v1 Announce Type: cross Abstract: Mechanistic interpretability often uses activation patching, causal tracing, path patching, and steering directions to reveal behaviorally meaningful
arXiv:2605.24686v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence
arXiv:2605.24300v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting s
arXiv:2605.24844v1 Announce Type: new Abstract: While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evoluti
I don't comment on every article that uses out-of-date measures on AI ability, but I felt (probably wrongly) that the article was a response to my viral tweet, so I felt I needed to say something! htt
arXiv:2605.25244v1 Announce Type: new Abstract: Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs
arXiv:2605.24699v1 Announce Type: new Abstract: Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can
arXiv:2505.23764v3 Announce Type: replace-cross Abstract: Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, h
Nine reasons why I warned OpenAI might fail and turn out to be the WeWork of AI, from two years ago. 9 reasons that OpenAI could someday be seen as the WeWork of AI: 👉 Lots of competitors are catching
arXiv:2605.24421v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data t
arXiv:2605.25281v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have made it increasingly difficult to distinguish human-written text from AI-generated content. Many
arXiv:2605.24834v1 Announce Type: cross Abstract: Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversar
this logic from 2024 held up pretty well considering all that’s changed. 9 reasons that OpenAI could someday be seen as the WeWork of AI: 👉 Lots of competitors are catching up. 👉 OpenAI has been force
arXiv:2605.24079v1 Announce Type: cross Abstract: Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), w
arXiv:2605.25133v1 Announce Type: new Abstract: Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference
arXiv:2603.11583v4 Announce Type: replace-cross Abstract: The success of a Large Language Model (LLM) task depends heavily on its prompt. Most use-cases specify prompts using natural language, which i
arXiv:2605.25988v1 Announce Type: new Abstract: Medical RAG needs evidence-grounded claims, so plugging a claim-level NLI checker into retrieval-augmented RL is intuitive. extbf{We find that the check
arXiv:2605.24069v1 Announce Type: cross Abstract: The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented
arXiv:2605.24579v1 Announce Type: new Abstract: Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression
An open source model has returned to #1 on the 3D Design leaderboard by Design Arena. Kimi K2.6 has reached the top of the leaderboard for 3D Design, ahead of models 10X more expensive like Opus 4.7 b
arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM
arXiv:2511.15503v2 Announce Type: replace-cross Abstract: High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Le
arXiv:2602.17653v2 Announce Type: replace Abstract: Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic reg
arXiv:2605.23094v1 Announce Type: cross Abstract: Generative augmentation is often proposed as a remedy for small medical-image datasets, but synthetic images are only useful when they improve downstr
arXiv:2605.23393v1 Announce Type: cross Abstract: Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route t
arXiv:2605.23238v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior i
arXiv:2605.22963v1 Announce Type: cross Abstract: Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated prop
arXiv:2605.23109v1 Announce Type: new Abstract: AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage t
arXiv:2605.23384v1 Announce Type: cross Abstract: Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement
arXiv:2605.23108v1 Announce Type: cross Abstract: AI-assisted code review tools typically operate as generic 'expert reviewer' agents, producing homogeneous findings regardless of the analysis type ne
arXiv:2605.23574v1 Announce Type: new Abstract: Long-horizon language agents can make many plausible local tool calls yet fail to persist until a requested count is actually complete. We study this ga
arXiv:2605.22875v1 Announce Type: new Abstract: We present extbf{Research Math Agents (RMA)}, an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies