March 2026

arXiv:2603.10071v1 Announce Type: new Abstract: Time series foundation models (TSFMs) are increasingly deployed in high-stakes domains, yet their internal representations remain opaque. We present the first application of sparse autoencoders (SAEs) to a TSFM, training TopK SAEs on activations of Chronos-T5-Large (710M parameters) across six layers. Through 392 single-feature ablation experiments, we establish that every ablated feature produces a positive CRPS degradation, confirming causal relevance. Our analysis reveals a depth-dependent hierarchy: early encoder layers encode low-level frequency features, […]

Ver mais

arXiv:2603.10069v1 Announce Type: new Abstract: Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools for a multi-turn information-seeking process autonomously. However, we identify a critical training instability that leads to catastrophic model collapse: Importance Sampling Distribution Drift(ISDD). In Group Relative Policy Optimization(GRPO), a widely adopted TARL algorithm, ISDD manifests as a precipitous decline in the importance sampling ratios, which nullifies gradient updates and triggers irreversible training failure. […]

Ver mais

arXiv:2603.10068v1 Announce Type: new Abstract: Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture how safety properties evolve under sustained adversarial interaction. We present ADVERSA, an automated red-teaming framework that measures guardrail degradation dynamics as continuous per-round compliance trajectories rather than discrete jailbreak events. ADVERSA uses a fine-tuned 70B attacker model (ADVERSA-Red, Llama-3.1-70B-Instruct with QLoRA) that eliminates the attacker-side safety refusals that render off-the-shelf models unreliable […]

Ver mais

arXiv:2603.10067v1 Announce Type: new Abstract: Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon’s orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes the training along noise-dominated directions. Motivated by the Heavy-Tailed Self-Regularization (HT-SR) theory, we propose HTMuon. HTMuon preserves Muon’s ability to capture parameter interdependencies while producing heavier-tailed updates and inducing heavier-tailed weight spectra. Experiments on LLM pretraining and image […]

Ver mais

arXiv:2603.10063v1 Announce Type: new Abstract: Collaborative healthcare research across multiple institutions increasingly requires diverse clinical datasets, but cross-border data sharing is strictly constrained by privacy regulations. Federated learning (FL) enables model training while keeping data local; however, many existing frameworks remain proof-of-concept and do not adequately address governance risks such as unauthorised participation, misuse, and lack of accountability. In particular, enforceable mechanisms for authentication, authorisation, and accounting (AAA) are often missing, limiting real-world clinical deployment. This paper presents […]

Ver mais

arXiv:2603.10062v1 Announce Type: new Abstract: As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer architecture problem. We distinguish shared and distributed memory paradigms, propose a three-layer memory hierarchy (I/O, cache, and memory), and identify two critical protocol gaps: cache sharing across agents and structured memory access control. We argue that the most pressing open challenge is multi-agent memory consistency. Our architectural framing provides […]

Ver mais

arXiv:2603.10060v1 Announce Type: new Abstract: AI agents that execute tasks via tool calls frequently hallucinate results – fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge proofs, which provide cryptographic guarantees but impose minutes of proving time per query, making them impractical for interactive agents. We propose NabaOS, a lightweight verification framework inspired by Indian epistemology (Nyaya Shastra), which classifies every claim in an LLM response by […]

Ver mais

arXiv:2603.10059v1 Announce Type: new Abstract: Flexible sensors are increasingly employed in soft robotics and wearable devices to provide proprioception of freeform deformations.Although supervised learning can train shape predictors from sensor signals, prediction accuracy strongly depends on sensor layout, which is typically determined heuristically or through trial-and-error. This work introduces a model-free, data-driven computational pipeline that jointly optimizes the number, length, and placement of flexible length-measurement sensors together with the parameters of a shape prediction network for large freeform […]

Ver mais

arXiv:2603.10057v1 Announce Type: new Abstract: Software supply-chain security requires provenance mechanisms that support reproducibility and vulnerability assessment under dynamic execution conditions. Conventional Software Bills of Materials (SBOMs) provide static dependency inventories but cannot capture runtime behaviour, environment drift, or exploitability context. This paper introduces agentic Artificial Intelligence Bills of Materials (AIBOMs), extending SBOMs into active provenance artefacts through autonomous, policy-constrained reasoning. We present an agentic AIBOM framework based on a multi-agent architecture comprising (i) a baseline environment reconstruction […]

Ver mais

arXiv:2603.10056v1 Announce Type: new Abstract: Most OAuth service providers, such as Google and Microsoft, offer only a limited range of coarse-grained data access. As a result, third-party OAuth applications often end up accessing more user data than necessary, even if their developers want to minimize data access. We present OAuthHub, a development framework that leverages users’ personal devices as the intermediary controller for OAuth-based data sharing between cloud services. The key innovations of OAuthHub are: (1) the insight […]

Ver mais