Knowledge catalogue
arXiv:2605.30907v1 Announce Type: cross Abstract: We present BlueFin, a benchmark that tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet wo
arXiv:2605.30448v1 Announce Type: cross Abstract: Black-box LLM distillation is usually evaluated as an output-matching problem: a student is considered successful when its responses are semantically
arXiv:2605.31073v1 Announce Type: new Abstract: Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do
arXiv:2605.30836v1 Announce Type: new Abstract: Recent SVD based compression methods for large language models like SVD LLM and Basis Sharing can be unified under one optimization problem. While mathe
arXiv:2605.30690v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents to reason coherently across extended interactions, personalize responses, and reuse past experience. Howeve
arXiv:2605.30712v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scr
arXiv:2605.31492v1 Announce Type: new Abstract: Large language models (LLMs) often solve reasoning problems by generating intermediate traces that explore and revise partial solutions. From a search p
arXiv:2605.30803v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric a
arXiv:2605.30723v1 Announce Type: new Abstract: LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon int
arXiv:2605.30537v1 Announce Type: new Abstract: Data selection is increasingly used to reduce the cost of large language model (LLM) fine-tuning, with recent methods prioritizing samples by current ut
arXiv:2605.29340v1 Announce Type: new Abstract: In this paper, we discuss question-answer dataset for LLM safety evaluation, with a focus on illegal activities. Specifically, on the basis of manual an
arXiv:2605.29018v1 Announce Type: new Abstract: Although a growing body of research has begun to describe user--LLM interactions, the picture it paints is largely static; little is known about how ind
arXiv:2605.29612v1 Announce Type: cross Abstract: Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over s
arXiv:2605.30103v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as generators in iterative neural architecture search (NAS), yet no formal convergence theory exists
arXiv:2510.20743v2 Announce Type: replace-cross Abstract: We present Empathic Prompting, a novel framework for multimodal human-AI interaction that enriches Large Language Model (LLM) conversations wi
arXiv:2605.29461v1 Announce Type: new Abstract: LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we iden
arXiv:2510.26270v2 Announce Type: replace Abstract: Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based re
arXiv:2605.29649v1 Announce Type: new Abstract: Heuristic search is the dominant paradigm in symbolic AI planning, and the strongest heuristics are the result of decades of work by planning researcher
arXiv:2605.29048v1 Announce Type: new Abstract: In this paper, we introduce LLMBridge, a new LLM based system for the task of end-to-end referential bridging resolution in English. Our bridging resolu
arXiv:2605.28876v1 Announce Type: cross Abstract: CI failure logs are large (median 5k lines, max 200k in this corpus) and noisy. Coding agents that try to debug them depend on an upstream tool to red
arXiv:2605.29440v1 Announce Type: cross Abstract: Retrieval-augmented LLM agents increasingly rely on curated skill banks: collections of reusable textual principles that guide decision making on comp
arXiv:2602.08567v2 Announce Type: replace-cross Abstract: Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value a
arXiv:2605.28918v1 Announce Type: new Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging
arXiv:2602.16610v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise
arXiv:2605.27789v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems are often compared by asking a large language model (LLM) judge which answer is better. For multi-hop RAG,
arXiv:2605.22166v2 Announce Type: replace Abstract: LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feed
arXiv:2605.28598v1 Announce Type: cross Abstract: LLM-powered social agents are increasingly used to simulate online social behavior, yet their realism remains difficult to validate. Existing work has
arXiv:2605.28483v1 Announce Type: new Abstract: Linking learning resources to a structured competency framework is key to enabling competency-based search and curriculum analytics in Learning Manageme
arXiv:2605.27766v1 Announce Type: new Abstract: LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongsi
arXiv:2605.27489v1 Announce Type: cross Abstract: Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretabilit
arXiv:2605.27914v1 Announce Type: cross Abstract: Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities satur
Release: llm-anthropic 0.25.1 New model: Claude Opus 4.8 (claude-opus-4.8). New -o fast 1 option for fast mode, for organizations with that feature enabled on their account. Default max_tokens for eac
arXiv:2602.15894v2 Announce Type: replace Abstract: In many large language model (LLM) alignment applications, users expect not only high-quality outputs but also substantial diversity. However, exist
arXiv:2605.28553v1 Announce Type: new Abstract: In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on
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:2605.11325v2 Announce Type: replace-cross Abstract: Every major benchmark for LLM memory systems, LoCoMo foremost, measures whether a model answered correctly, not whether the memory system retr
arXiv:2605.28557v1 Announce Type: cross Abstract: LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remain
arXiv:2605.27690v1 Announce Type: new Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long be
arXiv:2605.27593v1 Announce Type: new Abstract: Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collus
arXiv:2502.14321v3 Announce Type: replace-cross Abstract: Large language model-based multi-agent systems have recently gained significant attention due to their potential for complex, collaborative, a
arXiv:2605.26645v1 Announce Type: new Abstract: LLM-based knowledge-graph question answering (KGQA) delegates graph traversal to language models, turning each question into a sequence of local relatio
Cost controls are one of the main benefits of langsmith LLM gateway We’re seeing in a bunch of use cases adoption is getting to a point where cost really starts to matter Your agents can burn through
arXiv:2605.27354v1 Announce Type: cross Abstract: Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering la
arXiv:2605.26175v1 Announce Type: cross Abstract: Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activat
arXiv:2509.18384v2 Announce Type: replace Abstract: Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other do
arXiv:2605.26667v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empiric
NVIDIA's Blackwell GB200 NVL72 architecture achieved the fastest-ever results on the STAC-AI benchmark for financial LLM inference, delivering up to 3.2x single-GPU performance improvements over the p
arXiv:2605.27083v1 Announce Type: new Abstract: Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearning by training models to generate alternative fic
arXiv:2605.24216v1 Announce Type: cross Abstract: Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horiz
arXiv:2605.25200v1 Announce Type: new Abstract: Travel planning is a realistic task for evaluating the planning and tool-use abilities of LLM agents. However, existing benchmarks typically assume only
arXiv:2605.24659v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on unt
arXiv:2605.25141v1 Announce Type: cross Abstract: Reliable forecasting of renewable energy generation is a foundational requirement for grid stability energy trading battery scheduling and carbon awar
arXiv:2604.00499v2 Announce Type: replace Abstract: To schedule LLM inference, the extit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid he
arXiv:2605.25310v1 Announce Type: new Abstract: Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether t
arXiv:2605.23929v1 Announce Type: new Abstract: Modern AI systems increasingly rely on workflows composed of multiple interacting agents, some powered by large language models (LLMs) and others by con
arXiv:2605.24202v1 Announce Type: new Abstract: Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learn
arXiv:2605.26046v1 Announce Type: cross Abstract: Customizing an LLM judge to a specific task or domain often involves optimizing its prompt across multiple evaluation criteria simultaneously. Textual
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:2602.07235v2 Announce Type: replace-cross Abstract: Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into
arXiv:2605.23032v1 Announce Type: cross Abstract: Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment a