Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2608. 06377v1 Announce Type: cross Abstract: Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong.
arXiv:2608. 06283v1 Announce Type: new Abstract: We study the problem of sampling from target distributions whose potentials are simultaneously non-smooth, subject to superlinear gradient growth, and non-convex.
arXiv:2608. 05611v1 Announce Type: cross Abstract: Large Language Models (LLMs) can exhibit diverse personas, and activating expert personas has been shown to improve domain expertise and task accuracy.
arXiv:2608. 05166v1 Announce Type: cross Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings.
arXiv:2608. 05802v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored.
arXiv:2608. 06020v1 Announce Type: new Abstract: Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their beliefs and actions, and the market and institutional mechanisms through which their interactions produce aggregate outcomes.
arXiv:2601. 21124v2 Announce Type: replace-cross Abstract: Current multimodal LLMs process audio as a mono stream, ignoring the rich spatial information essential for embodied AI.
arXiv:2604. 09297v3 Announce Type: replace-cross Abstract: Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone.
arXiv:2608. 06253v1 Announce Type: new Abstract: Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations.
arXiv:2608. 05232v1 Announce Type: cross Abstract: The work of Tang et.
arXiv:2608. 05161v1 Announce Type: cross Abstract: Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved practical challenge.
arXiv:2608. 06310v1 Announce Type: new Abstract: Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models.
arXiv:2608. 05367v1 Announce Type: new Abstract: Counterfactual analysis aims to predict potential outcomes under hypothetical scenarios, offering valuable insights for decision-making.
arXiv:2608. 06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness.
arXiv:2608. 05371v1 Announce Type: new Abstract: World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning.
arXiv:2608. 06004v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) are currently the best approach to tabular prediction problems.
arXiv:2608. 05790v1 Announce Type: new Abstract: General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockchain environments.
arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.
arXiv:2608. 05872v1 Announce Type: cross Abstract: Standard Large Language Models (LLMs) execute layers sequentially.
arXiv:2608. 06197v1 Announce Type: new Abstract: Training large language model agents for long-horizon tool use typically relies on interactions with real or synthesized executable environments, whose construction and verification are costly, or on external simulators that are difficult to ground.