Search: “llm”

arXiv:2609.13816v1 Announce Type: cross Abstract: JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approach

arXiv:2609.14896v1 Announce Type: cross Abstract: A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at infere

arXiv:2609.14374v1 Announce Type: cross Abstract: Dynamic trajectory prediction has become an important paradigm for data-driven transient stability analysis (TSA), yet most existing predictors remain

arXiv:2609.14687v1 Announce Type: new Abstract: Data-to-text driver coaching is often presented as a generic pipeline from telematics events to advice. This paper argues that its content requires loca

arXiv:2609.15017v1 Announce Type: cross Abstract: Prompt-injection detectors are typically evaluated using aggregate F1 on in-distribution test data, which offers limited insight into behavior under d

arXiv:2609.15194v1 Announce Type: new Abstract: When a direct proof of a statement S seems hard or even impossible to obtain, there may exist another statement (or set of statements) S^{*}, somehow re

arXiv:2609.15544v1 Announce Type: cross Abstract: Enabling human stakeholders to specify reward functions that lead to their desired outcomes is a key challenge in deploying reinforcement learning age

arXiv:2609.13995v1 Announce Type: new Abstract: Debate over synthetic data in marketing research has polarized between claims that large language models (LLMs) make human respondents obsolete and call

arXiv:2609.13334v1 Announce Type: cross Abstract: Enterprise AI agents often succeed in a demonstration and then stall once they must operate day after day. An industry report estimates that most pilo

arXiv:2609.15079v1 Announce Type: cross Abstract: Multi-agent LLM architectures, such as LangChain and AutoGen, largely assume English as the lingua franca for internal inter-agent communication, even

arXiv:2509.19375v2 Announce Type: replace-cross Abstract: Large language models are increasingly used for clinical text classification, where overconfident misclassifications can directly affect patie

arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also int

arXiv:2609.15397v1 Announce Type: new Abstract: AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative executio

arXiv:2609.12471v1 Announce Type: new Abstract: We introduce AMDKernelVault, an open HIP and Triton kernel corpus and training framework for recent AMD CDNA GPUs. Existing LLM-based kernel agents are

arXiv:2606.16000v3 Announce Type: replace Abstract: We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agen

arXiv:2609.11961v1 Announce Type: new Abstract: Stress is a pervasive determinant of mental health and a key target for mobile health interventions. On-device language models (ODLMs) offer privacy-pre

arXiv:2609.12686v1 Announce Type: cross Abstract: Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increas

Well, I’d add one more with myself, as one with a PhD in biology and another PhD in AI and now working in both, to make n=2. Generating a hypothetical genome blueprint of a virus from LLM versus gener

arXiv:2609.11660v1 Announce Type: new Abstract: In recent years, artificial intelligence has made extraordinary progress thanks to large-scale models capable of generalization and the generation of co

It's well known that agents hack benchmark rewards. The usual response is a patch for each task that gets exploited. In a study of 456 adjudicated trajectories from more than 31,000 public agent runs,

arXiv:2609.11319v1 Announce Type: new Abstract: Most of mathematical knowledge has been communicated through so-called informal use of mathematics and natural language. With large language models (LLM

arXiv:2609.11294v1 Announce Type: new Abstract: High-fanout agent workloads create a growing memory bottleneck because a single task may spawn many concurrent sandbox sessions. Yet these sandboxes are

arXiv:2609.11867v1 Announce Type: new Abstract: We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed

arXiv:2609.11884v1 Announce Type: cross Abstract: Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residu

arXiv:2609.11504v1 Announce Type: new Abstract: A structurally valid DeFi workflow can still authorize a costly trade. We introduce DeFiFlowBench, a benchmark of 207 team-authored prompts for natural-

arXiv:2609.11334v1 Announce Type: new Abstract: Natural Language Inference processes pairs of sentences to extract their semantic relations. NLI has been a hot research topic, integrated as a main com

arXiv:2609.10658v1 Announce Type: new Abstract: Activation steering provides a lightweight way to control large language models (LLMs) by modifying their hidden activations at inference time. Among th

arXiv:2609.11261v1 Announce Type: cross Abstract: Five decades of litigation have disgorged hundreds of millions of pages of formerly secret business records from the tobacco industry, along with docu

arXiv:2609.09671v1 Announce Type: cross Abstract: When an agent writes code, the development framework becomes the control system for a non-deterministic worker. Spec-first, agent-driven frameworks ha

arXiv:2606.21844v2 Announce Type: replace Abstract: As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing B

arXiv:2609.11163v1 Announce Type: cross Abstract: Structured pruning of large language models (LLMs) offers hardware-efficient compression, yet existing methods require calibration data, gradient comp

arXiv:2508.05830v3 Announce Type: replace Abstract: Large Language Model (LLM) studies that use language responses elicited from depression assessments to predict scores on those same assessments ofte

arXiv:2609.11769v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to analyze and rewrite news, yet current framing studies mainly evaluate generation, detection, or wh

arXiv:2609.10901v1 Announce Type: new Abstract: LLM search agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a search strategy requires understanding how credible

arXiv:2607.18116v2 Announce Type: replace-cross Abstract: Recent work leverages Large Language Models (LLMs) to generate executable code for pedagogical animations using libraries such as Manim. Howev

arXiv:2609.09242v1 Announce Type: cross Abstract: Large Language Models (LLMs) often generate natural-language comments while writing code, and these comments become part of the context used to genera

arXiv:2609.05587v1 Announce Type: new Abstract: Existing evaluations of tool-using agents primarily measure whether an agent can successfully complete diverse tasks with tools. These evaluations gener

arXiv:2405.02228v4 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly generate citation-backed responses, yet citation hallucination remains a major challenge for trustwo

arXiv:2609.05446v1 Announce Type: new Abstract: We introduce AutoFyn, an agent harness inspired by the Expert Iteration algorithm, adapting a frozen model across many rounds by updating persistent sta

arXiv:2602.14488v3 Announce Type: replace-cross Abstract: IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive

arXiv:2609.05947v1 Announce Type: new Abstract: Peer review is central to quality control in science. However, existing evaluations of AI-assisted peer review mainly focus on the overall quality of ge

arXiv:2609.09575v1 Announce Type: new Abstract: Topic models summarize large text corpora, but top-ranked words often provide only a limited representation of topic semantics. Sparse autoencoders (SAE

arXiv:2609.07247v1 Announce Type: new Abstract: Scaling the interaction horizon-the maximum number of environment interactions per episode-improves LLM agents on long-horizon tasks, and curriculum-bas

arXiv:2609.06027v1 Announce Type: cross Abstract: Search-augmented LLM agents are increasingly used for consumer decisions, making them vulnerable to Generative Engine Optimization (GEO) poisoning. Ex

arXiv:2609.08435v2 Announce Type: new Abstract: In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier informati

arXiv:2609.07573v1 Announce Type: new Abstract: Multi-agent LLM deliberation has been explored as a scalable way to simulate public deliberation. For such simulations to be informative, persona agents