arXiv:2605.03195v1 Announce Type: new Abstract: Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibilities like search, debugging or terminal execution. This architectural pattern keeps the main agent’s context window clean by isolating verbose outputs (e.g. build logs, test results, etc.) within the subagent context. Typically […]
Gated Subspace Inference for Transformer Acceleration
arXiv:2605.03109v1 Announce Type: cross Abstract: A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and a residual, computes the linear-layer output on the subspace component via a cached low-rank […]
Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forests
arXiv:2508.14936v3 Announce Type: replace Abstract: Synthetic data holds substantial potential to address practical challenges in epidemiology due to restricted data access and privacy concerns. However, many current methods suffer from limited quality, high computational demands, and complexity for non-experts. Furthermore, common evaluation strategies for synthetic data often fail to directly reflect statistical utility and measure […]
Pact: A Choreographic Language for Agentic Ecosystems
arXiv:2605.03143v1 Announce Type: cross Abstract: Recent advances in large language models have led to the rise of software systems (i.e. agents) that execute with increasing autonomy on behalf of users in open, multi-party settings, interacting with untrusted counterparts and managing private information. Choreographic programming offers correct-by-construction protocol-design for such settings, but assumes cooperative participants — […]
Stop Automating Peer Review Without Rigorous Evaluation
arXiv:2605.03202v1 Announce Type: new Abstract: Large language models offer a tempting solution to address the peer review crisis. This position paper argues that today’s AI systems should not be used to produce paper reviews. We ground this position in an empirical comparison of human- versus AI-generated ICLR 2026 reviews and an evaluation of the effect […]
MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
arXiv:2605.03228v1 Announce Type: cross Abstract: As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives improbable in single-turn settings. Such long-horizon threats pose significant risks to the safe deployment of LLM agents in critical domains. […]
Ortho-Hydra: Orthogonalized Experts for DiT LoRA
arXiv:2605.03252v1 Announce Type: cross Abstract: LoRA fine-tuning of diffusion transformers (DiT) on multi-style data suffers from emphstyle bleed: a single low-rank residual cannot represent several distinct artist fingerprints, and the optimizer converges to their average. Mixture-of-experts LoRA in the HydraLoRA style replaces the up-projection with $E$ heads under a router, but when every expert is […]
Taking the GP Out of the Loop
arXiv:2506.12818v3 Announce Type: replace-cross Abstract: Bayesian optimization (BO) has traditionally solved black-box problems where function evaluation is expensive and, therefore, observations are few. Recently, however, there has been growing interest in applying BO to problems where function evaluation is cheaper and observations are more plentiful. In this regime, scaling to many observations $N$ is impeded […]
Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs
arXiv:2605.03227v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning. However, their ability to perform exact, deterministic computation remains unclear. In this work, we systematically evaluate multiple prompting strategies, including Chain-of-Thought (CoT), Least-to-Most decomposition, Program-of-Thought (PoT), and Self-Consistency (SC), on tasks requiring precise and error-free outputs, […]
AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
arXiv:2605.03317v1 Announce Type: cross Abstract: Representation alignment has recently emerged as an effective paradigm for accelerating Diffusion Transformer training. Despite their success, existing alignment methods typically impose a fixed supervision target or a fixed alignment granularity throughout the entire denoising trajectory, whether the guidance is provided by external vision encoders, internal self-representations, or VAE-derived features. […]
Can LLMs Make (Personalized) Access Control Decisions?
arXiv:2511.20284v2 Announce Type: replace-cross Abstract: Precise access control decisions are crucial for the security of both traditional applications and emerging agent-based systems. Typically, these decisions are made by users during app installation or at runtime. However, due to the increasing complexity and automation of systems, making access control decisions can impose a significant cognitive burden […]
cotomi Act: Learning to Automate Work by Watching You
arXiv:2605.03231v1 Announce Type: new Abstract: What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from user behavior. For execution, an agent scaffold with adaptive lazy observation, verbal-diff-based history compression, coarse-grained […]