Knowledge catalogue
arXiv:2610.02267v1 Announce Type: new Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input
arXiv:2603.29112v2 Announce Type: replace Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in rec
Great overview of context compression in LLM Agents And one interesting, unexpected finding. If your compaction policy is tuned to cut tokens, it may be making your agent run slower. Great study from
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:2610.02841v1 Announce Type: new Abstract: LLMs are known to introduce stylistic changes into generated text, yet how these stylistic shifts affect model decisions on scientific tasks remains und
arXiv:2610.03296v1 Announce Type: new Abstract: Complex reasoning queries can be decomposed into directed acyclic task graphs and distributed across heterogeneous LLMs, reducing latency through parall
arXiv:2610.02670v1 Announce Type: cross Abstract: LLM agents are known to be slow in rollouts. An agent completes a task one step at a time. At each step, it reasons and then chooses an action to exec
Haven't seen posted here. The research project matters because it proves you can pull trustworthy decisions straight out of an LLM's internal state in a single forward pass (no generation loop, no par
arXiv:2610.03195v1 Announce Type: new Abstract: As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (th
Yann LeCun's latest talk at ETH Zürich 'You should not work on LLM. At least if you're in academia, you should absolutely not work on LLMs. There is nothing you can bring to the table. If you're inter
arXiv:2610.01451v1 Announce Type: new Abstract: Personalized interpretation of health checkup results requires reasoning across longitudinal records, medical knowledge, lifestyle guidance, and healthc
arXiv:2610.00870v1 Announce Type: new Abstract: We present an educator-guided LLM pedagogical agent for scaffolded feedback in conceptual database design. Integrated into an entity--relationship diagr
I mean , DeepSeek, Kimi, GLM, MiniMax -- the list of Chinese LLM's is such a long freaking list. As American's -- why don't we feel .. a little funny .. about being so far behind? Chinese entrepreneur
Cool eval. Simply ask an LLM “Land or Water?” and give it a latitude and longitude coordinate as text. Ask 16,200 times, plot as image. The models know. From compressing the internet. results for all
arXiv:2610.01000v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as probabilistic generators for simulation, synthetic data generation, and decision support in settin
arXiv:2610.01014v1 Announce Type: new Abstract: Voting over multiple LLM responses is a common primitive in test-time scaling and ensemble inference. Collecting more responses can expand the candidate
arXiv:2610.01223v1 Announce Type: cross Abstract: Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the
arXiv:2610.00675v1 Announce Type: cross Abstract: Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but
arXiv:2610.00687v1 Announce Type: cross Abstract: Hardware-operable failures (HOFs) interrupt large language model (LLM) training but permit recovery on the same hardware without reset, repair, or rep
arXiv:2610.02199v1 Announce Type: new Abstract: Full-parameter fine-tuning of large language models (LLMs) incurs substantial optimizer state memory overhead, limiting the model sizes that fit on mode
arXiv:2610.00054v1 Announce Type: cross Abstract: Reading an LLM judge's verdict from the logits of its first generated token is cheap, requires no generation, and is exactly what constrained decoding
arXiv:2610.00833v1 Announce Type: cross Abstract: Fluent LLM explanations may not follow the evidence from a structured system. We present VERITYGATE, a four-gate checker for declared evidence IDs, en
arXiv:2609.33153v2 Announce Type: replace-cross Abstract: Reported improvements from tools and reusable skills in large language model agents refer to different comparisons. This critical narrative re
arXiv:2610.00163v1 Announce Type: cross Abstract: Complex problem solving depends on acting effectively and understanding how a system works. AI advice may support these outcomes unequally. Two prereg
arXiv:2601.22028v2 Announce Type: replace Abstract: Most LLM unlearning methods aim to approximate retrain-from-scratch behaviors with minimal distribution shift, often via alignment-style objectives
arXiv:2609.38789v1 Announce Type: new Abstract: Reconstruction errors in multivariate time-series anomaly detection may not reliably distinguish abnormal behavior from benign deviations. Language-deri
arXiv:2609.38929v1 Announce Type: new Abstract: Machine learning systems increasingly face the need to remove the influence of entire data domains, such as toxic language, harmful behavior, or topical
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:2609.38458v1 Announce Type: new Abstract: Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Pri
arXiv:2609.39807v1 Announce Type: cross Abstract: Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicate
arXiv:2609.39049v1 Announce Type: cross Abstract: A large language model (LLM) can rate depression severity directly from a social media post or mark which clinical criteria the post shows and let cod
arXiv:2609.39001v1 Announce Type: cross Abstract: LLM services are billed per token and context windows are measured in tokens, yet the number of tokens needed for the same content varies across langu
arXiv:2609.36104v1 Announce Type: new Abstract: Replacing one LLM agent with a collaborating team can raise accuracy, but whether scaling the team helps, and which architecture to scale, is unclear. S
Building a local voice chat pipeline: Struggling with fast, natural PT-BR conversation models I'm currently trying to build a local AI voice chat system that can use tools via an LLM. I'm testing tw
arXiv:2609.36888v1 Announce Type: new Abstract: Mixed human-LLM documents require locating authorship transitions from detector scores whose reliability varies across text units. Existing weighted mea
arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collabora
arXiv:2607.17247v2 Announce Type: replace-cross Abstract: Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two p
arXiv:2609.36365v1 Announce Type: new Abstract: Can interaction formats and textual scaffolds help large language model (LLM) agents make better decisions, and do better decisions come with better exp
arXiv:2609.37590v1 Announce Type: new Abstract: LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation fr
arXiv:2609.36739v1 Announce Type: cross Abstract: Multi-agent LLM systems are increasingly structured like organizations, with roles, critics and shared memory, yet they are evaluated on tasks that la
I run local models through Ollama and kept hitting the same quiet problems, so I wrote a scanner for them. llm-doctor checks your model stores (Ollama, LM Studio, Hugging Face, MLX) for duplicate weig
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs h
arXiv:2609.37111v1 Announce Type: new Abstract: Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Existi
arXiv:2609.37127v1 Announce Type: new Abstract: Establishing unbranding as a critical practice to prevent visual logos from acquiring negative connotations is standard in image generation. Large Langu
LLM utility has increased, and deeper understanding to a degree, but I still very much agree with this post from 2020 @GaryMarcus Forgets GPT~3. Real #AI news of 2020 is that @ylecun & Y Bengio have c
arXiv:2609.35873v1 Announce Type: new Abstract: Automated generation of LLM harnesses promises to improve inference through task specialization. Yet additional answer coverage can arise from repeated
arXiv:2609.37322v1 Announce Type: new Abstract: Rubric-based evaluation is widely used to assess LLM-based systems by decomposing response quality into task-specific scoring criteria. However, automat
arXiv:2609.37221v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed to solve complex scientific and practical problems via iterative optimization. However, dynamical
arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of
arXiv:2609.35928v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly
arXiv:2609.37554v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as high-level planners in robot navigation, but their outputs may become unreliable when instructio
arXiv:2609.37402v1 Announce Type: new Abstract: Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such
arXiv:2609.35908v1 Announce Type: cross Abstract: Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely
arXiv:2609.37172v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuris
arXiv:2609.37858v1 Announce Type: cross Abstract: Many localized large language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optim
arXiv:2609.37196v1 Announce Type: cross Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowi
arXiv:2609.36855v1 Announce Type: new Abstract: Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful info
arXiv:2609.31675v1 Announce Type: new Abstract: We introduce the Active Causal Discovery Benchmark (ACDB), an SCM-grounded environment for evaluating whether LLM agents recover causal graph structure
arXiv:2609.35257v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization offers a memory-efficient alternative for LLM fine-tuning by estimating updates only from forward evaluations of perturbe
arXiv:2609.31704v1 Announce Type: cross Abstract: Large language models are increasingly used as interacting agents, but it remains unclear how robust their coordination is when public communication i