arXiv:2605.01749v1 Announce Type: new
Abstract: Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors compound across reasoning steps. Existing approach…
arXiv:2601.12024v2 Announce Type: replace
Abstract: Customer reviews contain valuable signals about service quality, but converting large-scale review corpora into actionable business recommendations remains difficult. Standard sentiment/aspect analys…
arXiv:2604.27924v2 Announce Type: replace-cross
Abstract: Peer review is a multi-stage process involving reviews, rebuttals, meta-reviews, final decisions, and subsequent manuscript revisions. Recent advances in large language models (LLMs) have motiv…
arXiv:2602.05353v3 Announce Type: replace
Abstract: Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and control due to opaque internal workflows. While some framew…
arXiv:2605.01844v1 Announce Type: new
Abstract: Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representa…
arXiv:2602.18700v2 Announce Type: replace-cross
Abstract: LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model generation, and m…
arXiv:2605.01520v1 Announce Type: cross
Abstract: Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning with Verifiable Rewar…
arXiv:2602.22480v2 Announce Type: replace
Abstract: An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks …
arXiv:2605.01591v1 Announce Type: cross
Abstract: Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surrogate models, limitin…
arXiv:2604.16506v2 Announce Type: replace-cross
Abstract: Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple images rather than interpreting a single view. …