Search: “claude”

arXiv:2607.22513v1 Announce Type: cross Abstract: Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor

arXiv:2606.18543v2 Announce Type: replace Abstract: Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real

arXiv:2607.14186v4 Announce Type: replace-cross Abstract: Scaling executable agent training data for LLM post-training is bottlenecked by substrate-bound methods that tie task generation to predefined

arXiv:2607.13080v1 Announce Type: cross Abstract: Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-

arXiv:2607.13039v1 Announce Type: cross Abstract: Safety evaluations for dual-use biology assistants often measure base-model capability, refusal behavior, or jailbreak success. These metrics miss a d

arXiv:2607.12713v1 Announce Type: cross Abstract: Generated tokens are a direct driver of the cost, latency, and energy of generative AI (GAI) code editing. We show the format of feedback is a lever o

arXiv:2607.12796v1 Announce Type: cross Abstract: When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer ever

arXiv:2607.08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods m

arXiv:2607.08054v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly trusted to draft the artifacts of safety analysis such as, losses, hazards, Unsafe Control Actions (UCAs

arXiv:2607.07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single 'pipe

arXiv:2607.06341v1 Announce Type: cross Abstract: Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers

arXiv:2607.06411v1 Announce Type: cross Abstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of

arXiv:2607.05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security ha

arXiv:2607.04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA. For emerging AI accelerators such as AWS Trainium and

arXiv:2602.20629v3 Announce Type: replace Abstract: As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated ev

arXiv:2607.03968v1 Announce Type: cross Abstract: Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks, generate and edit files, run code, and refine ou

arXiv:2507.02950v3 Announce Type: replace-cross Abstract: Large language models (LLMs) may support counseling training, yet evidence from Japanese-language interactions and automated quality ratings r

arXiv:2607.02175v1 Announce Type: new Abstract: Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinic

arXiv:2607.02007v1 Announce Type: new Abstract: Large language models now score near ceiling on general benchmarks, but these aggregate measures reveal little about how models behave within single dis

arXiv:2607.01247v1 Announce Type: cross Abstract: Open-ended mathematics exams are valuable because they assess reasoning, proof construction, algorithmic thinking, and communication of intermediate s

arXiv:2607.02469v1 Announce Type: cross Abstract: Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing

arXiv:2606.13715v2 Announce Type: replace Abstract: The best agent on WorkBench in March 2024, GPT-4, completed just 43% of tasks. We revisit the benchmark in June 2026 and find that the best agent to

arXiv:2606.29213v1 Announce Type: new Abstract: OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on

arXiv:2606.29537v1 Announce Type: new Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to

arXiv:2606.28480v1 Announce Type: cross Abstract: As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader ra

arXiv:2606.18142v3 Announce Type: replace Abstract: AI agents are moving from advisors to actors, booking travel, planning menus, and running procurement on behalf of users. Existing benchmarks for AI

arXiv:2606.16821v2 Announce Type: replace Abstract: Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that

arXiv:2606.24370v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into decision-support roles in business and policy contexts. While prior benchmark studies have

arXiv:2606.22269v1 Announce Type: cross Abstract: We investigate the translation quality of current large language models (LLMs) for English-to-Hausa and English-to-Fongbe - two typologically distinct

arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic eval

arXiv:2606.11204v1 Announce Type: new Abstract: Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document forma

arXiv:2601.12164v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as analytical tools across multilingual contexts, yet their outputs may carry systemati

arXiv:2606.10106v1 Announce Type: cross Abstract: The term agent harness now circulates widely in software engineering with generative artificial intelligence. It names the layer that wraps a language

arXiv:2606.08036v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in academic research workflows, but scholarly tasks require high factual precision and therefore ex

arXiv:2606.07591v1 Announce Type: cross Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We presen

arXiv:2606.09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedde

arXiv:2602.08235v2 Announce Type: replace-cross Abstract: Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unin

arXiv:2606.07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the mod

arXiv:2606.06788v1 Announce Type: new Abstract: Evaluations of large language models (LLMs) in scientific information seeking tasks have become increasingly use-centric, such as conducting live or mul

arXiv:2602.04894v4 Announce Type: replace-cross Abstract: LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities

arXiv:2606.05670v1 Announce Type: new Abstract: Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and

arXiv:2606.05158v1 Announce Type: cross Abstract: Multi-agent reasoning systems adopt a 'generate-then-transfer' paradigm that forces end-to-end latency to scale linearly with pipeline depth. We intro

arXiv:2606.03641v1 Announce Type: new Abstract: We investigate whether large language models produce different medical triage recommendations for identical neurological symptoms when only the patient'

arXiv:2606.02630v1 Announce Type: cross Abstract: Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke author

arXiv:2606.01136v1 Announce Type: new Abstract: Single-score translation metrics can conflate legitimate variation with error, a problem especially acute for classical languages where multiple defensi

arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode colla