arXiv:2610.36717v1 Announce Type: new Abstract: When expanding a report, writing with agents may introduce a stronger claim than the article makes and then disclaim it. This is called over-defensive writing. We assume that this is because the agent is writing for responding to an adversarial AI reviewer, instead of a human reader. The defensive context may also influnce the consequent when we simply ban defensive writing in the output through prompts. In order to reduce over-defensive writing, w
arXiv:2610.36734v1 Announce Type: new Abstract: Continual learning requires large language models to acquire new knowledge and capabilities while retaining what they have learned. Fine-tuning and replay support acquisition and retention, but deciding whether incoming examples need supervision and which historical examples to revisit remains a challenge. We propose Compatibility-Aware Memory Replay (CAMR), an adaptive framework that jointly controls current-example supervision and historical repl
arXiv:2610.36759v1 Announce Type: new Abstract: Multilingual multi-hop document question answering (MMHop-DocQA) requires locating and integrating evidence across complex layouts, document pages, and diverse languages. Existing approaches include single-pass processing and adaptive tool use, but learning to coordinate evidence acquisition, cross-page integration, and answer verification remains challenging. To address this challenge, we present DocSkill, an agentic framework with a learned skill
arXiv:2610.36797v1 Announce Type: new Abstract: Reading "While the man hunted the deer ran into the woods" requires giving up the analysis in which "the deer" is the object of "hunted". People who have just read such a sentence still produce more transitive structures, so the abandoned analysis primes later language. We ask whether language models keep using an analysis they have abandoned, and what in the model carries it. In 24 open models from 124M to 70B parameters, a garden-path sentence le
arXiv:2610.36805v1 Announce Type: new Abstract: Controlling the personality of a language model usually relies on written profiles or named trait categories, so it can only express what an author writes down or what a taxonomy names. We instead propose Personality Latents (PL), which learn a latent for each person from their own writing, with no personality labels and no authored profile, and inject it into a frozen language model as a soft prefix. Following generative latent optimization, each
arXiv:2610.36811v1 Announce Type: new Abstract: Knowledge improvement in large language models is shifting from predefined knowledge incorporation pipelines toward evaluation-guided updating. Existing methods use evaluation to localize model-specific knowledge weaknesses and guide targeted post-training. However, identifying what to improve does not necessarily provide sufficient information for deciding how to improve it. The same localized weakness can be compatible with distinct operational k
arXiv:2610.36813v1 Announce Type: new Abstract: Web systems increasingly predict users' decisions from what users say, yet when interests partly conflict, users may promise to cooperate to win the other side's cooperation and then not do so. Sales or service agents that rely on such promises may grant concessions to users who then do not keep their promises, at a cost to the party they represent. We test how LLMs combine users' statements with decision records to predict users' decisions, using
In today’s digital marketplace, video content dictates ad performance and search rankings. However, traditional video production is slow, expensive, and difficult to scale. AivideosUGC solves this bottleneck. As a leading AI-powered UGC creation platform, AivideosUGC Turn product URL, image, or prompt into authentic, high-converting UGC video ads in minutes for TikTok, Reels, and YouTube Shorts.with Ai video agent and Ai actors ,ready-to-use video templates.
AI UGC (Artificial Intelligence User-Generated Content) is the automated creation of casual, creator-style review and unboxing videos using AI avatars, AI scriptwriters, and realistic voiceovers. It replaces traditional human influencers, saving brands time and money on production. AivideosUGC solves this bottleneck. As a leading AI-powered UGC creation platform, AivideosUGC Turn product URL, image, or prompt into authentic, high-converting UGC video ads in minutes for TikTok, Reels, and YouTube