arXiv:2604.08033v1 Announce Type: new Abstract: Intelligent systems powered by large-scale sensor networks are shifting from predefined monitoring to intent-driven operation, revealing a critical Semantic-to-Physical Mapping Gap. While large language models (LLMs) excel at semantic understanding, existing perception-centric pipelines operate retrospectively, overlooking the fundamental decision of what to sense and when. We formalize this proactive decision […]
Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
arXiv:2604.08169v1 Announce Type: new Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors are encoded as linear structure in activation space, making it tractable via steering, while safety alignment has been shown to […]
From Phenomenological Fitting to Endogenous Deduction: A Paradigm Leap via Meta-Principle Physics Architecture
arXiv:2604.08245v1 Announce Type: new Abstract: The essence of current neural network architectures is phenomenological fitting: they learn input-output statistical correlations via massive parameters and data, yet lack intrinsic understanding of the fundamental principles governing physical reality. This paper proposes a paradigm leap from pure phenomenological fitting to the fusion of phenomenological fitting and endogenous deduction. […]
ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection
arXiv:2604.08326v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with high-stakes medical standards remains a significant challenge, primarily due to the dissonance between coarse-grained preference signals and the complex, multi-dimensional nature of clinical protocols. To bridge this gap, we introduce ProMedical, a unified alignment framework grounded in fine-grained clinical criteria. We first construct ProMedical-Preference-50k, […]
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
arXiv:2604.08377v1 Announce Type: new Abstract: Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from […]
On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities
arXiv:2604.08424v1 Announce Type: new Abstract: The increasing autonomy of spacecraft demands fault-detection systems that are both reliable and explainable. This work addresses eXplainable Artificial Intelligence for onboard Fault Detection, Isolation and Recovery within the Attitude and Orbit Control Subsystem by introducing a framework that enhances interpretability in neural anomaly detectors. We propose a method to […]
SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
arXiv:2604.08477v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly improved large language model (LLM) reasoning in formal domains such as mathematics and code. Despite these advancements, LLMs still struggle with general reasoning tasks requiring capabilities such as causal inference and temporal understanding. Extending RLVR to general reasoning is fundamentally constrained by […]
Prediction Arena: Benchmarking AI Models on Real-World Prediction Markets
arXiv:2604.07355v1 Announce Type: cross Abstract: We introduce Prediction Arena, a benchmark for evaluating AI models’ predictive accuracy and decision-making by enabling them to trade autonomously on live prediction markets with real capital. Unlike synthetic benchmarks, Prediction Arena tests models in environments where trades execute on actual exchanges (Kalshi and Polymarket), providing objective ground truth that […]
Hidden Biases in Conditioning Autoregressive Models
arXiv:2604.07855v1 Announce Type: new Abstract: Large language and music models are increasingly used for constrained generation: rhyming lines, fixed meter, inpainting or infilling, positional endings, and other global form requirements. These systems often perform strikingly well, but the induced procedures are usually not exact conditioning of the underlying autoregressive model. This creates a hidden inferential […]
DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues
arXiv:2604.07895v1 Announce Type: new Abstract: Selecting an appropriate background music (BGM) that supports natural human conversation is a common production step in media and interactive systems. In this paper, we introduce dialogue-conditioned BGM recommendation, where a model should select non-intrusive, fitting music for a multi-turn conversation that often contains no music descriptors. To study this […]
Capture-Quiet Decomposition: A Verification Theorem for Chess Endgame Tablebases
arXiv:2604.07907v1 Announce Type: new Abstract: We present the Capture-Quiet Decomposition (CQD), a structural theorem for verifying Win-Draw-Loss (WDL) labelings of chess endgame tablebases. The theorem decomposes every legal position into exactly one of three categories — terminal, capture, or quiet — and shows that a WDL labeling is correct if and only if: (1) terminal […]
EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
arXiv:2604.07927v1 Announce Type: new Abstract: Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research agents still rely on implicit, unstructured search behavior that causes redundant exploration and brittle evidence aggregation. Motivated by Anthropic’s “think” tool paradigm and insights from the […]