Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2604. 10842v3 Announce Type: replace-cross Abstract: LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context Protocol (MCP) to read and write files on a developer's workstation.
arXiv:2606. 07790v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on communication protocols for coordination, yet their robustness under adversarial and structural constraints remains poorly understood.
arXiv:2606. 08633v1 Announce Type: new Abstract: Long-horizon maritime trajectory prediction is important for shipping management, logistics planning, and maritime risk analysis, yet month-level forecasting remains insufficiently studied.
arXiv:2606. 09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query.
arXiv:2606. 08446v1 Announce Type: cross Abstract: Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive.
arXiv:2605. 05138v2 Announce Type: replace Abstract: We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting.
arXiv:2601. 07013v2 Announce Type: replace-cross Abstract: Traditional filtering algorithms for state estimation -- such as classical Kalman filtering, unscented Kalman filtering, and particle filters -- show performance degradation when applied to nonlinear systems whose uncertainty follows arbitrary non-Gaussian, and potentially multi-modal distributions.
arXiv:2601. 02424v2 Announce Type: replace-cross Abstract: The synthesis of nanocrystals has been highly dependent on trial-and-error, due to the complex correlation between synthesis parameters and physicochemical properties.
arXiv:2602. 05774v4 Announce Type: replace-cross Abstract: Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single greedy trajectories, decoding involves verifying and ranking multiple sampled draft paths.
arXiv:2606. 09577v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks.
arXiv:2606. 09630v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies provide strong priors for language-conditioned manipulation, but remain brittle in off-nominal states requiring targeted recovery.
arXiv:2606. 07620v1 Announce Type: cross Abstract: With the growth of Vision Transformers in safety-critical domains like autonomous systems and medical imaging, ensuring their reliability against soft errors is paramount.
arXiv:2602. 00238v2 Announce Type: replace-cross Abstract: Existing retrieval-augmented generation (RAG) systems often assume that each query has a single correct answer.
arXiv:2606. 08777v1 Announce Type: cross Abstract: Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a principled understanding of how robust such predictions are under counterfactual perturbations.
arXiv:2605. 29823v2 Announce Type: replace Abstract: Deep networks often exhibit a preference for "simple" solutions, and such a simplicity bias is widely believed to play a key role in generalization.
arXiv:2606. 08658v1 Announce Type: new Abstract: LLMs have revolutionized knowledge representation and retrieval, but lack the explicit modeling that knowledge ontologies possess.
arXiv:2606. 07726v1 Announce Type: new Abstract: Large Language Models are typically benchmarked by evaluating every model on every test query.
arXiv:2606. 08200v1 Announce Type: new Abstract: Evaluating LLM-powered interactive social agents is challenging because socially relevant behaviors depend not only on isolated outputs, but also on prior interactions, social roles, and downstream actions.
arXiv:2606. 09551v1 Announce Type: cross Abstract: Two-server secure inference allows a client to query a hosted large language model (LLM) without revealing prompts or embeddings.
arXiv:2606. 08018v1 Announce Type: new Abstract: Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects.