Evolutionary Generation of Multi-Agent Systems
arXiv:2602.06511v3 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but design
Knowledge catalogue
arXiv:2602.06511v3 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but design
arXiv:2605.21362v1 Announce Type: new Abstract: Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial pro
arXiv:2605.20242v1 Announce Type: new Abstract: Efficient discovery of precursor additives is essential for improving the performance of perovskite solar cells, yet the large chemical space makes conv
arXiv:2602.06025v2 Announce Type: replace Abstract: Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offl
arXiv:2605.21463v1 Announce Type: new Abstract: We present Mem-pi, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrie
arXiv:2605.20404v1 Announce Type: new Abstract: The rapid adoption of Generative AI, including LLM-based chatbots like ChatGPT, has highlighted the need for accessible ways to support public understan
arXiv:2605.20868v1 Announce Type: new Abstract: KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empiric
arXiv:2602.06358v2 Announce Type: replace Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapte
arXiv:2605.20364v1 Announce Type: new Abstract: Automatic evaluation of long-form literary writing remains challenging, as generic LLM-as-Judge approaches may not fully capture creativity-related dime
arXiv:2605.19944v1 Announce Type: cross Abstract: While empirical scaling laws for LLM reasoning are well-documented, the theoretical mechanisms governing out-of-distribution (OOD) generalization rema
arXiv:2510.05746v2 Announce Type: replace Abstract: Large Language Model (LLM)-powered Multi-agent systems (MAS) have achieved state-of-the-art results on various complex reasoning tasks. Recent works
B9251 is a build identifier for a release in the llama.cpp project, which enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the clo
b9253 is the latest version of llama.cpp, released on May 20, 2026. Llama.cpp is a project for LLM inference in C/C++. This build includes bug fixes, performance improvements, and features for running
arXiv:2605.20084v1 Announce Type: cross Abstract: Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the
arXiv:2605.19229v1 Announce Type: new Abstract: Survey research faces mounting structural challenges: declining response rates, sample bias, block-wise missingness among at-risk respondents, and AI-as
CANTANTE addresses the challenge of optimizing LLM-based multi-agent systems where system-level performance scores are available but individual agent parameters cannot be directly optimized. The frame
arXiv:2605.19735v1 Announce Type: cross Abstract: Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on larg
arXiv:2605.18810v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffus
arXiv:2507.10614v2 Announce Type: replace-cross Abstract: The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLM
arXiv:2605.20022v1 Announce Type: new Abstract: Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and
arXiv:2605.19266v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems are typically optimized for verbatim transcription, which preserves disfluencies, filler words, and informa
arXiv:2605.19141v1 Announce Type: cross Abstract: Large language models are increasingly deployed as automated judges to evaluate the strength of arguments. As this role expands, their legitimacy depe
arXiv:2604.17237v2 Announce Type: replace-cross Abstract: Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over auto
How fast is 10 tokens per second really? Neat little HTML app by Mike Veerman (source code here) which simulates LLM token output speeds from 5/second to 800/second. Useful if you see a model advertis
arXiv:2605.18772v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language model (LLM) outputs by grounding generation in external knowledge
Its The Graph again (not the METR graph, the one from the o1 launch). Although no logarithmic decay of ability with increasing compute... This is a general-purpose LLM. It wasn’t targeted at this prob
arXiv:2605.19330v1 Announce Type: new Abstract: LLM agents organize behavior through skills - structured natural-language specifications governing how an agent reasons, retrieves, and responds. Unlike
arXiv:2605.19276v1 Announce Type: new Abstract: In recent years, the field of artificial intelligence has undergone a paradigm shift from task-specific small-scale models to general-purpose large lang
arXiv:2602.17038v3 Announce Type: replace Abstract: Reinforcement learning (RL) has equipped LLM agents with a strong ability to solve complex tasks. However, existing RL methods normally use a single
arXiv:2605.20061v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactiv
arXiv:2603.05910v2 Announce Type: replace Abstract: LLM-powered tool-calling agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Y
arXiv:2605.19035v1 Announce Type: new Abstract: The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents
wait… did Cohere just release Command A+ models under Apache 2.0 for the first time ever?! 🙊 welcome to Europe! 🤗 Introducing: Cohere Command A+ We’ve created our most powerful LLM yet, optimized it t
arXiv:2605.19447v1 Announce Type: new Abstract: Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failur
arXiv:2605.20023v1 Announce Type: new Abstract: Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by
arXiv:2601.09722v2 Announce Type: replace-cross Abstract: In this work, we present an annotation framework that demonstrates how a multilingual LLM pretrained on a large corpus can be used as a teache
arXiv:2605.18133v1 Announce Type: cross Abstract: LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These ca
arXiv:2605.17435v1 Announce Type: new Abstract: Biomedical question answering often requires decisions from retrieved literature whose relevance, quality, and support for candidate answers are uneven.
arXiv:2605.17528v1 Announce Type: cross Abstract: Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the t
arXiv:2605.18226v1 Announce Type: cross Abstract: Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While pref
arXiv:2605.17450v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used for automated vulnerability repair (AVR), where repository-level reasoning enables them to ins
arXiv:2605.17721v1 Announce Type: new Abstract: Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions,
arXiv:2605.17246v1 Announce Type: cross Abstract: We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a c
arXiv:2605.18721v1 Announce Type: cross Abstract: Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable
arXiv:2605.17849v1 Announce Type: cross Abstract: LLM pretraining is shifting from a compute-bound to a data-bound regime, where available human (organic) text falls far short of scaling demands. Howe
arXiv:2605.18663v1 Announce Type: new Abstract: As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or remo
arXiv:2605.16714v1 Announce Type: new Abstract: Security knowledge graphs can provide computable external memory for security agents, but constructing them from long-form cyber threat intelligence (CT
arXiv:2605.17873v1 Announce Type: cross Abstract: Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not whi
arXiv:2602.01705v3 Announce Type: replace-cross Abstract: Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete to
arXiv:2601.01685v2 Announce Type: replace-cross Abstract: As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an
arXiv:2605.16821v1 Announce Type: new Abstract: The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple parad
arXiv:2602.02262v3 Announce Type: replace-cross Abstract: LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require
arXiv:2605.16551v1 Announce Type: new Abstract: Evaluating LLM-based agents remains challenging because identifying meaningful failure cases often requires substantial human effort to design realistic
arXiv:2603.08462v2 Announce Type: replace Abstract: ac{CoT} prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing ``Budget Forcing'' methods red
arXiv:2605.16874v1 Announce Type: new Abstract: Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood
arXiv:2508.06974v2 Announce Type: replace Abstract: 1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LL
arXiv:2605.16650v1 Announce Type: cross Abstract: Evaluating multi-turn dialogue systems remains challenging because response quality depends not only on the current prompt, but also on previously est
arXiv:2602.14211v2 Announce Type: replace-cross Abstract: Agent skills are increasingly used to extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources. While im
arXiv:2605.18401v1 Announce Type: cross Abstract: Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills a
arXiv:2605.17348v1 Announce Type: new Abstract: Recent advancements in LLM-based multi-agent systems have demonstrated remarkable collaborative capabilities across complex tasks. To improve overall ef