Knowledge catalogue
arXiv:2608.14109v1 Announce Type: new Abstract: Autonomous LLM agents are increasingly deployed in complex real-world workflows, yet they remain vulnerable to runtime behavioral drift, a silent deviat
arXiv:2608.14352v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents are increasingly used for complex tasks such as software testing and cybersecurity assessment. While these age
arXiv:2608.14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on per
arXiv:2608.14229v1 Announce Type: new Abstract: Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM unlearning methods apply uniform g
arXiv:2608.13921v1 Announce Type: new Abstract: LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can
arXiv:2608.12522v1 Announce Type: new Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize eac
arXiv:2608.13326v1 Announce Type: new Abstract: LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a cont
arXiv:2608.12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state. An unsafe success can thereby become reusable policy after i
arXiv:2608.11295v1 Announce Type: cross Abstract: Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met dur
arXiv:2608.12273v1 Announce Type: cross Abstract: LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progre
arXiv:2608.11381v1 Announce Type: new Abstract: We study whether the localized numerical operations and integrative judgments of financial analysis benefit from the same form of LLM specialization. La
arXiv:2608.11241v1 Announce Type: new Abstract: Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: genera
arXiv:2608.11878v1 Announce Type: cross Abstract: Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. Howeve
arXiv:2608.11676v1 Announce Type: new Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redun
arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these
arXiv:2608.10441v1 Announce Type: cross Abstract: Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expen
arXiv:2509.23452v2 Announce Type: replace-cross Abstract: Current text-to-image generation models, even state-of-the-art models, exhibit a significant performance gap when spatial expressions are desc
arXiv:2608.10149v1 Announce Type: new Abstract: Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples. Ensemble learning addresses this
arXiv:2604.02621v2 Announce Type: replace Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely e
arXiv:2608.11045v1 Announce Type: cross Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (
arXiv:2608.10528v1 Announce Type: cross Abstract: Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost. We
arXiv:2607.28646v2 Announce Type: cross Abstract: This article analyses narrative mechanisms that are common in dialogues with LLM chatbots. In combination, these mechanisms produce an interactional s
arXiv:2603.00077v3 Announce Type: replace-cross Abstract: Rubric-based LLM judges have become indispensable for evaluating and optimizing systems on non-verifiable tasks, where success cannot be reduc
arXiv:2608.09292v1 Announce Type: cross Abstract: Self-evolving methods improve the capabilities of LLM agents by sampling trajectories from the underlying LLMs and learning from these trajectories. H
arXiv:2608.09555v1 Announce Type: new Abstract: External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effe
arXiv:2608.08284v1 Announce Type: new Abstract: Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable in
arXiv:2608.08189v1 Announce Type: new Abstract: LLM-driven program discovery relies on rapid evaluator feedback, but many scientific and engineering tasks require high-fidelity simulations, hardware e
arXiv:2502.11027v5 Announce Type: replace Abstract: Large language model (LLM) scaling inference is key to unlocking greater performance, and leveraging diversity has proven an effective way to enhanc
arXiv:2608.08245v1 Announce Type: cross Abstract: LLM applications deployed at scale face a fundamental challenge: privacy constraints prevent direct inspection of user interactions, making it difficu
arXiv:2608.06992v1 Announce Type: cross Abstract: We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a large language model (LLM). GPTKB 2.0 contains
arXiv:2608.06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., cl
Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments. Quantization
Simon @disiok proposed a novel IQ test for language models, asking whether an LLM becomes smarter or dumber after being fine‑tuned on a user’s stream of consciousness. The tweet was posted on 9 Aug 20
Zain (@zainhas) published a detailed article on August 7, 2026 explaining that autoscaling for highly peaky large‑language‑model (LLM) inference is fundamentally different from autoscaling conventiona
arXiv:2608.05695v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible cons
arXiv:2608.05446v1 Announce Type: cross Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse ex
arXiv:2608.05541v1 Announce Type: new Abstract: Evolution Strategy (ES) is a promising alternative to gradient-based fine-tuning for resource-constrained Large Language Model (LLM) reasoning. However,
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long
arXiv:2608.04053v1 Announce Type: cross Abstract: Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous e
arXiv:2608.04588v1 Announce Type: cross Abstract: Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing sy
arXiv:2512.02567v2 Announce Type: replace-cross Abstract: The advent of strong generative AI has a considerable impact on various software engineering tasks such as code repair, test generation, or la
arXiv:2608.04307v1 Announce Type: cross Abstract: Text summarization is deceptively difficult. While condensing information seems straightforward, real-world enterprise summarization of support ticket
arXiv:2608.04265v1 Announce Type: cross Abstract: Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed. In strategic cyber-physical systems, a stronger
arXiv:2608.04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so th
arXiv:2608.03591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to
arXiv:2608.03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attribu
arXiv:2608.03838v1 Announce Type: new Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent
arXiv:2608.03239v1 Announce Type: new Abstract: Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create impli
arXiv:2608.02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researche
arXiv:2608.02645v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on external tools to perform multistage tasks. Existing agent frameworks typically assume that tool calls are a
arXiv:2608.02391v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive. Evolution st
arXiv:2608.00979v1 Announce Type: cross Abstract: Large language models are increasingly used as synthetic research participants and are often validated by whether their marginal responses resemble hu
arXiv:2608.02464v1 Announce Type: cross Abstract: LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the stan
arXiv:2607.28968v1 Announce Type: cross Abstract: Renault, Bergeaud, and Bosquet (hereafter RBB) argue that dating LLM adoption as the first month in which an author's abstract is flagged induces a st
Finally a good paper testing whether agent memory needs an LLM at all. Production memory stacks spend extra model calls on summarizing interactions, writing records, and reranking retrievals. Every on
arXiv:2607.28947v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to solve complex problems by searching over program space, offering a general paradigm for scientific
arXiv:2607.28908v1 Announce Type: new Abstract: Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers. Large language models (LLMs) are increasi
arXiv:2607.28887v1 Announce Type: cross Abstract: Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder t
arXiv:2607.29678v1 Announce Type: new Abstract: LLM serving systems cache prompt KV state, yet most front ends still re-tokenize the full request text on every call. The cost lands on coding agents, w
arXiv:2607.26120v1 Announce Type: new Abstract: Large Language Models (LLMs)-powered multi-agent systems are increasingly deployed in mixed-motive environments, where agents operate under asymmetric i