PACE: A Proxy for Agentic Capability Evaluation
arXiv:2607.02032v1 Announce Type: new Abstract: Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure. A single evaluation c
Knowledge catalogue
arXiv:2607.02032v1 Announce Type: new Abstract: Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure. A single evaluation c
arXiv:2607.02214v1 Announce Type: new Abstract: Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires
arXiv:2607.00007v1 Announce Type: cross Abstract: Large language model (LLM)-based web agents reduce manual scripting for web data collection, yet on live websites, they often miss relevant pages, ret
arXiv:2607.01104v1 Announce Type: cross Abstract: In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via
arXiv:2607.00016v1 Announce Type: cross Abstract: Information localization within massive repositories is a cornerstone of agentic LLM systems. While synthetic data-driven optimization has proven succ
Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, effective coordination
arXiv:2607.00890v1 Announce Type: new Abstract: Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic
arXiv:2607.00224v1 Announce Type: cross Abstract: Watermarking promises a statistical trace of large language model (LLM) use, but real documents, after editing or paraphrasing, rarely arrive as purel
arXiv:2607.01136v1 Announce Type: cross Abstract: Agent skills package reusable operational knowledge for Large Language Model (LLM) agents, yet as they grow in scope, they become dependency-bearing a
wikis! LLM Wikis are being slept on. I argue that creating knowledge bases with LLMs or coding agents is one of the most valuable applications of AI today. It's about being intentional in building and
arXiv:2606.31229v1 Announce Type: new Abstract: Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. How
arXiv:2606.30949v1 Announce Type: new Abstract: High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challen
arXiv:2606.30840v1 Announce Type: new Abstract: LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR eval
arXiv:2606.19501v2 Announce Type: replace Abstract: Decentralized finance exposes supervisors to fast-moving, networked credit risks. General-purpose LLM agents fit this setting poorly: they over-read
arXiv:2606.31484v1 Announce Type: cross Abstract: Parallel thinking has enjoyed great success for boosting LLM performance on reasoning tasks without the need for any re-training. However, existing me
arXiv:2606.31250v1 Announce Type: cross Abstract: Large language models (LLM) trained on web-scale corpora generate output that may infringe copyright, yet existing technical safeguards focus narrowly
We call ours Operational Language Wiki, essentially a pattern for building memory to fill in the delta between the “dialect” of a team vs the “world language” that the LLM is trained on. Use it to cap
B9847 is a build release in the llama.cpp project, which is an open-source tool that enables LLM inference with minimal setup on a wide range of hardware . This specific build release likely contains
arXiv:2501.14940v4 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety ben
arXiv:2406.03367v2 Announce Type: replace Abstract: Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planni
arXiv:2606.29280v1 Announce Type: cross Abstract: We identify intervention bias as a previously unquantified failure mode of zero-shot large-language-model (LLM) educational advisory agents: without t
arXiv:2606.29793v1 Announce Type: new Abstract: Demand for personalized financial advising is growing, but consistent advisor expertise is difficult to obtain, scale, and encode in LLM systems. Simple
arXiv:2606.14202v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have advanced Automatic Heuristic Design (AHD) by enabling heuristic generation through reasoning and code synthe
arXiv:2606.30077v1 Announce Type: cross Abstract: With Large Language Model (LLM) pre-training and fine-tuning shifting its focus from data volume to data quality, quality data selection has emerged a
arXiv:2606.28392v1 Announce Type: cross Abstract: Accurate lesion segmentation in PET/CT is critical for oncology, yet remains challenging because physiologic tracer uptake and artifacts can mimic mal
arXiv:2606.29532v1 Announce Type: cross Abstract: Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A
arXiv:2606.30372v1 Announce Type: new Abstract: Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling b
arXiv:2308.05201v4 Announce Type: replace Abstract: Large Language Model (LLM)-based generative AI systems are general-purpose tools capable of augmenting or even automating a wide range of job functi
arXiv:2606.27483v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-hor
arXiv:2606.27397v1 Announce Type: cross Abstract: Evaluating LLM agents requires dynamic environments that go beyond static reasoning and zero-sum games. Real-world economic interaction is often open-
arXiv:2606.27681v1 Announce Type: cross Abstract: World models in partially observed environments rely on latent representations that summarize interaction history, but in many modern LLM-based archit
arXiv:2606.26327v1 Announce Type: cross Abstract: In actor-critic reinforcement learning, network architectures are typically manually designed. Automating this design is challenging because each cand
arXiv:2606.27136v1 Announce Type: new Abstract: For LLM agents in multi-step interactive environments, a key challenge is to make effective use of accumulated interaction experience. Existing work has
arXiv:2606.19336v2 Announce Type: replace Abstract: Learning to simulate human users in interactive settings could advance the training of agent assistants, evaluation of personalization systems, rese
arXiv:2606.27027v1 Announce Type: cross Abstract: With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become fo
arXiv:2606.18430v2 Announce Type: replace Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals
arXiv:2606.26836v1 Announce Type: new Abstract: Existing benchmarks typically report accuracy for a single model on a single run. This systematically understates real-world LLM capabilities, particula
arXiv:2606.27242v1 Announce Type: cross Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequ
arXiv:2606.25705v1 Announce Type: new Abstract: LLM agents are increasingly being used to automate tasks for users within an open GUI environment. They inevitably encounter screens containing user-sen
arXiv:2606.25404v1 Announce Type: new Abstract: Large Language Models (LLMs) can reason over complex instructions but often fail to satisfy the physical and spatial constraints required for robotic ta
arXiv:2606.25198v1 Announce Type: new Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-base
arXiv:2606.25369v1 Announce Type: cross Abstract: While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on Englis
arXiv:2606.23913v1 Announce Type: new Abstract: This article develops an architecture that creates a formally verifiable reward signal to train legal AI, adapting the LLM proposes, verifier disposes p
arXiv:2606.24414v1 Announce Type: new Abstract: Formal verification produces machine-checkable certificates that attest to the satisfaction or violation of temporal properties, yet these certificates
arXiv:2606.24820v1 Announce Type: new Abstract: LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated l
arXiv:2606.24004v1 Announce Type: cross Abstract: Steering a large language model (LLM) toward a desired behavior typically relies on an iterative process of hand-crafting a prompt based on a careful
arXiv:2606.20702v1 Announce Type: new Abstract: Vision-language models (VLMs) have sparked growing interest in zero-shot Earth Observation (EO) downstream tasks, with further gains enabled by remote-s
DFlash is an open source block diffusion model for speculative decoding that significantly accelerates LLM inference on NVIDIA Blackwell GPUs by drafting entire token blocks in parallel and verifying
arXiv:2606.22079v1 Announce Type: cross Abstract: Web data curation has been widely studied for decoder Large Language Model (LLM) pretraining. Encoders for dense-terminology domains such as medicine,
arXiv:2601.21817v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm.
arXiv:2606.12003v1 Announce Type: new Abstract: Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on
Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude Big scoop for Maxwell Zeff at Wired: “We’re changing Fable 5’s safeguards for frontier LLM development to make them
arXiv:2606.11213v1 Announce Type: new Abstract: We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a
arXiv:2606.11722v1 Announce Type: cross Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (
arXiv:2606.11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes. We introduce My Chem
arXiv:2606.11371v1 Announce Type: cross Abstract: Spoken language, whether produced by humans or large language models (LLM), unfolds over time with varying semantic content. However, we still lack si
arXiv:2606.12199v1 Announce Type: cross Abstract: Spoken dialogue models typically start from text LLM backbones, yet reasoning often degrades when conditioning on speech instead of text. We attribute
arXiv:2606.10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effec
arXiv:2510.09801v3 Announce Type: replace Abstract: While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of re
arXiv:2606.09916v1 Announce Type: cross Abstract: Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning. Both KV memory and KV read b