It Takes Workflows to Evolve Better Workflows
arXiv:2610.01026v1 Announce Type: cross Abstract: Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that
Knowledge catalogue
arXiv:2610.01026v1 Announce Type: cross Abstract: Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that
arXiv:2609.33289v2 Announce Type: replace Abstract: Autonomous large language model (LLM) agents operating in multi-product markets must make sequential decisions under information asymmetry and resou
arXiv:2610.01118v1 Announce Type: cross Abstract: A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what t
arXiv:2610.01058v1 Announce Type: cross Abstract: Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization wea
Hi! This is a new benchmark that I created together with other researchers at Meta, Stanford, Harvard, UW. Most benchmarks these days seem to test models to just fix a bug that I as a user already enc
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:2610.00672v1 Announce Type: new Abstract: Protein foundation models support mutation-effect and structural prediction, but predictive performance alone does not reveal which forms of biological
arXiv:2610.01143v1 Announce Type: cross Abstract: Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group pr
I've been using my free time during weeknights and weekends for the last 11 months working on and refining a small domain-specific language model. It specializes on information about World War II. The
arXiv:2610.01165v1 Announce Type: new Abstract: Layer interventions are widely used to probe the internal organization of language models, yet most analyses examine a single training checkpoint even t
arXiv:2610.00940v1 Announce Type: cross Abstract: We propose ReHoPER, an inference-only, zero-shot method that improves large language models' reasoning by generating and answering intermediate questi
arXiv:2610.02033v1 Announce Type: new Abstract: Individual mobility trajectories support urban analysis and location-based services, yet most trajectory generators require observations from their depl
arXiv:2610.00996v1 Announce Type: new Abstract: Reliable roll prediction of unmanned surface vehicles (USVs) is essential for ensuring navi?gational safety and enhancing autonomous decision-making. Wh
arXiv:2610.00400v1 Announce Type: cross Abstract: Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcomes, challenging defenses that assess actions or
arXiv:2610.00093v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from
arXiv:2610.01892v1 Announce Type: cross Abstract: Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning t
arXiv:2610.00805v1 Announce Type: cross Abstract: Editing a chest radiograph requires completing the requested change while preserving unrelated content. We study a latent diffusion editor with an ins
Super interesting paper from Meta Superintelligence Labs on controlling long agent runs. They use the same workers and same budget, and ProgramBench goes from 63.7% to 71.5% with GPT-5.5 when a dedica
arXiv:2610.00403v1 Announce Type: new Abstract: A network can fit its training examples while failing to recover the rule that generated their labels. We examine this separation in single-hidden-layer
arXiv:2610.01323v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often refuse a harmful request but comply once the same goal is spread over several turns. Preference object
arXiv:2610.01984v1 Announce Type: cross Abstract: Byte-level byte-pair encoding (BBPE) tokenizers are attractive for multilingual large language models (LLMs) because they cover all Unicode text. In U
arXiv:2610.00411v1 Announce Type: new Abstract: Contemporary Genomic Foundation Models (GFMs) rely on a DNA-as-a-string paradigm that employs masked token prediction objectives for pretraining. Howeve
arXiv:2601.12758v2 Announce Type: replace-cross Abstract: As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preferenc
arXiv:2511.00763v3 Announce Type: replace Abstract: We investigate the performance of large language models (LLMs) on repetitive deterministic prediction tasks and study how the sequence accuracy rate
arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. Howev
arXiv:2609.38447v1 Announce Type: new Abstract: Reliable, timely crop-yield forecasts are essential for market stability and risk management, yet many approaches rely on costly or hard-to-scale inputs
arXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a
arXiv:2609.40353v1 Announce Type: new Abstract: The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general
arXiv:2609.39441v1 Announce Type: cross Abstract: Online reinforcement learning has been extended to flow matching for diffusion model (DM) image generation. However, this paradigm faces three limitat
arXiv:2609.39081v1 Announce Type: cross Abstract: We spent five weeks using an LLM coding agent on open problems in coding theory: finding large sets of four-letter words, such as DNA barcodes, that s
arXiv:2609.39924v1 Announce Type: cross Abstract: Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, ma
arXiv:2609.38856v1 Announce Type: new Abstract: The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent featu
arXiv:2609.38510v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive LLMs by having a lightweight drafter propose tokens that the target model verifies in parallel. Diffusio
arXiv:2609.35356v2 Announce Type: replace Abstract: Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted gene
arXiv:2609.38357v1 Announce Type: new Abstract: Conversational safety evaluations often test language models with a single harmful prompt, even though real-world systems interact with users through lo
arXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents
arXiv:2609.39102v1 Announce Type: cross Abstract: Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers the
Hi everyone — I'm behind Autonomous Workday, and I'm sharing an English-language architecture walkthrough about building an event-driven workflow around local inference. The proposed flow separates fi
arXiv:2609.38585v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) routing methods score LLMs independently to select top-k models. However, this ignores model correlations and enfo
arXiv:2609.39383v1 Announce Type: cross Abstract: Large language model (LLM)-based automatic heuristic design (AHD) iteratively proposes and refines heuristics, pairing design rationales with executab
arXiv:2609.40148v1 Announce Type: new Abstract: Power-law learning curves are often treated as fixed properties of a model and its data, although learning-rate and batch-size schedules can change the
arXiv:2511.16030v3 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) enables efficient, high-fidelity novel view synthesis, yet its performance degrades severely under sparse-view supervis
arXiv:2609.38748v1 Announce Type: new Abstract: Recent joint video-audio generation models have achieved strong semantic correspondence and temporal synchronization. However, applications such as AR/V
A few days ago I released Jeff-Qwen3.5-0.8B, a small 'System 1' model that picks between options you define and returns a calibrated probability for each, in one forward pass. Speed was great on my M4
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:2609.38383v1 Announce Type: new Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without polic
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:2609.40286v1 Announce Type: cross Abstract: Unlearning a fact in one language does not guarantee its removal in others as changing the query or even the requested answer language can reopen seem
arXiv:2609.39018v1 Announce Type: cross Abstract: Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code
arXiv:2609.39107v1 Announce Type: new Abstract: Large Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and b
arXiv:2609.38460v1 Announce Type: new Abstract: Language agents must revise planned actions when evidence changes, permission is revoked, or a stop instruction arrives. A useful response is selective:
arXiv:2609.39915v1 Announce Type: new Abstract: Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents
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:2609.38593v1 Announce Type: cross Abstract: Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incor
arXiv:2609.38632v1 Announce Type: new Abstract: Recent probabilistic weather forecasters train stochastic predictors with the continuous ranked probability score (CRPS) to generate each ensemble membe
arXiv:2609.38869v1 Announce Type: new Abstract: In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to unde
arXiv:2609.38914v1 Announce Type: new Abstract: Evaluating interactive agents is expensive. Agent behavior is stochastic, so reliability must be measured over repeated trials, but failures are rare an
arXiv:2609.38545v1 Announce Type: cross Abstract: Machine-learning signals built from financial text treat what institutions say, and what the media repeat, as evidence about value. But whoever shapes
arXiv:2609.39560v1 Announce Type: new Abstract: Sampling several responses and voting over their answers can improve a language model's accuracy, but repeated answers limit the benefit of additional s
arXiv:2609.39296v1 Announce Type: new Abstract: Video semantic communication has attracted increasing attention as a promising approach to improving video transmission efficiency. However, most existi