Knowledge catalogue
arXiv:2608.12419v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable breakthroughs across various applications. However, their architectures remain inefficient in pret
neurosymbolic world models – *exactly* what I argued for in 2020 in the Next Decade in AI – for the win. Jeremy's excellent work here is a great illustration of a very powerful type of approach: LLM-g
arXiv:2608.12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily
arXiv:2608.12905v1 Announce Type: new Abstract: The behavior of contemporary generative Large Language Models (LLMs) is directly shaped by prompts, unstructured texts that describe the desired output
arXiv:2512.13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing contro
arXiv:2608.13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, b
arXiv:2608.13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-
arXiv:2606.20077v2 Announce Type: replace-cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interac
arXiv:2507.14267v2 Announce Type: replace Abstract: Large language model (LLM) agents can execute long-horizon scientific workflows, but their numerical outputs are difficult to trust: agents lose con
arXiv:2608.10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions
arXiv:2608.10319v1 Announce Type: cross Abstract: Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks. As devel
arXiv:2602.01747v2 Announce Type: replace Abstract: Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world setting
arXiv:2608.09939v1 Announce Type: cross Abstract: Production teams deploying LLM chat agents face a specific quality assurance gap: existing evaluation tools test individual responses or simulate soci
arXiv:2602.16481v2 Announce Type: replace Abstract: Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of
arXiv:2608.10743v1 Announce Type: new Abstract: Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are s
We’re excited to announce DiG-bench, a new benchmark for discovery! Over the last few weeks we’ve been testing frontier AI models on our novel discovery games and seeing how they score. Each game is a
arXiv:2608.09184v1 Announce Type: new Abstract: Large language model (LLM) agents provide a promising interface for command-line-based network operations, but a plausible command may still fail or int
arXiv:2608.07651v1 Announce Type: new Abstract: Large language models (LLMs) show promise in medical image interpretation but suffer from hallucination, limited accuracy, and run-to-run inconsistency.
arXiv:2608.08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding maliciou
arXiv:2512.11614v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on retrieved context to guide large language models (LLM), yet treats the retrieval as a heuristic
arXiv:2608.09732v1 Announce Type: cross Abstract: Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find th
arXiv:2608.09443v1 Announce Type: new Abstract: Large language model (LLM) agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on
arXiv:2608.07494v1 Announce Type: cross Abstract: AI tools like ChatGPT and DeepSeek, powered by Large Language Models (LLMs), allow users to obtain instant and effective content responses simply by t
arXiv:2608.08236v1 Announce Type: new Abstract: Multi-agent LLM systems often fail not for lack of candidate answers, but because they have no persistent mechanism for deciding which incompatible clai
arXiv:2608.09742v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) represents large language model (LLM) updates with two compact matrix factors, i.e., A and B, providing an efficient way to
arXiv:2608.08037v1 Announce Type: new Abstract: LLM-based agent frameworks now act as personal assistants for multi-step tasks. Existing agent frameworks such as OpenClaw commonly follow the Cloud Age
On August 11 2026, Gary Marcus commented that if the symbolic components were removed from Claude’s Riemann implementation it would fail to work, highlighting a concrete win for hybrid neurosymbolic A
Not even sure if I'm allowed to post this, what with the 'completely/primarily LLM generated copy' rule (the post itself is fine, but the repo/model I'm sharing definitely is, whoops) and the whole li
arXiv:2608.09044v1 Announce Type: new Abstract: Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically r
arXiv:2608.07978v1 Announce Type: cross Abstract: Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving
arXiv:2608.07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims tha
arXiv:2608.06849v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs. Existing sparse attention and KV-compression
model-saver : fix expert shared/chunk FFN length key clobber (#26693) The saver called add_kv with LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH twice, the second time passing n_ff_chexp. gguf_set_val_u32
I've been comparing Cline / Kilo / Qwen Code lately since they all handle long-task state differently. Cline: has Focus Chain, a markdown file kept outside the conversation that gets reinjected on a c
arXiv:2608.06977v1 Announce Type: new Abstract: It is well established that large language models (LLMs) are sensitive to prompt framing, reflecting patterns in their training data or prior prompts. I
arXiv:2511.12738v2 Announce Type: replace Abstract: Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive l
arXiv:2608.06530v1 Announce Type: new Abstract: Planning a degree from official university sources requires solving two problems in order. The institution's curriculum must first be reconstructed from
arXiv:2608.06638v1 Announce Type: cross Abstract: Mechanistic interpretability of music generation has concentrated on audio models, leaving symbolic models largely unexplored. We analyze two public t
arXiv:2608.06723v1 Announce Type: cross Abstract: The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making ac
arXiv:2608.06607v1 Announce Type: new Abstract: Most document-extraction systems use a single model for all documents. This is simple but can be costly for easy cases and less effective for difficult
arXiv:2608.06792v1 Announce Type: cross Abstract: Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foun
When @QualiaQuanta took a shot at the Riemann, half in jest, people called her a crackpot. When Anthropic uses Claude to do the same thing, it gets a hundred thousand views in 30 minutes. It might wel
arXiv:2608.05179v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used across the scientific research lifecycle: ideation, literature search, experiment design and e
arXiv:2608.05152v1 Announce Type: cross Abstract: Large language models (LLMs) with chain-of-thought reasoning have been widely applied in recent years, and theoretical explanations of their behavior
arXiv:2608.05573v1 Announce Type: new Abstract: LLM agents increasingly execute long-horizon tasks through tool use and environment interaction, shifting evaluation from final-response scoring to veri
arXiv:2608.05004v1 Announce Type: new Abstract: Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including 'delusi
arXiv:2608.04205v1 Announce Type: new Abstract: Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract aw
arXiv:2608.03154v1 Announce Type: new Abstract: Biomedical relation extraction (BioRE) extracts structured knowledge from biomedical literature for applications such as knowledge base construction and
arXiv:2608.03119v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning but typically relies on ground-truth (GT) answers, limiting scalability. Vo
arXiv:2608.03233v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable potential for analogy making, a core cognitive capability that drives novelty and creativity.
arXiv:2607.28587v2 Announce Type: replace-cross Abstract: SWE-bench-like benchmarks are widely used for evaluating LLM's issue resolution capability. They typically follow a common construction pipeli
arXiv:2608.03062v1 Announce Type: new Abstract: LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operation
arXiv:2608.03018v1 Announce Type: new Abstract: Modern cities rely on an increasing number of digital services to operate, but residents' daily needs are still difficult to meet. Services are fragment
arXiv:2608.03137v1 Announce Type: new Abstract: Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon i
arXiv:2608.01679v2 Announce Type: replace Abstract: Persistent memory allows (self-evolving) LLM agents to adapt across tasks by consolidating heterogeneous interaction histories into reusable facts,
arXiv:2608.00316v1 Announce Type: new Abstract: Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by
arXiv:2608.00717v1 Announce Type: cross Abstract: Rubric-based AI systems for thesis assessment use criterion weights to assign different levels of importance to evaluation criteria. These weights are
arXiv:2608.00782v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relativ
arXiv:2608.02087v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM
arXiv:2510.20449v2 Announce Type: replace Abstract: Instruction tuning is crucial for aligning Large Language Models (LLMs), yet the quality of instruction-following data varies significantly. While h