arXiv:2604.09101v1 Announce Type: cross Abstract: Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service (MLaaS) providers, who adapt vision-language models (VLMs) such as CLIP to downstream tasks via prompt tuning rather than training from scratch. This semi-honest setting creates a security risk where a malicious provider can […]
Yes, But Not Always. Generative AI Needs Nuanced Opt-in
arXiv:2604.09413v1 Announce Type: cross Abstract: This paper argues that a one-size-fits-all approach to specifying consent for the use of creative works in generative AI is insufficient. Real-world ownership and rights holder structures, the imitation of artistic styles and likeness, and the limitless contexts of use of AI outputs make the status quo of binary consent […]
Persona-E$^2$: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events
arXiv:2604.09162v1 Announce Type: cross Abstract: Most affective computing research treats emotion as a static property of text, focusing on the writer’s sentiment while overlooking the reader’s perspective. This approach ignores how individual personalities lead to diverse emotional appraisals of the same event. Although role-playing Large Language Models (LLMs) attempt to simulate such nuanced reactions, they […]
Artifacts as Memory Beyond the Agent Boundary
arXiv:2604.08756v1 Announce Type: new Abstract: The situated view of cognition holds that intelligent behavior depends not only on internal memory, but on an agent’s active use of environmental resources. Here, we begin formalizing this intuition within Reinforcement Learning (RL). We introduce a mathematical framing for how the environment can functionally serve as an agent’s memory, […]
Semantic Rate-Distortion for Bounded Multi-Agent Communication: Capacity-Derived Semantic Spaces and the Communication Cost of Alignment
arXiv:2604.09521v1 Announce Type: cross Abstract: When two agents of different computational capacities interact with the same environment, they need not compress a common semantic alphabet differently; they can induce different semantic alphabets altogether. We show that the quotient POMDP $Q_m,T(M)$ – the unique coarsest abstraction consistent with an agent’s capacity – serves as a capacity-derived […]
Hidden in Plain Sight: Visual-to-Symbolic Analytical Solution Inference from Field Visualizations
arXiv:2604.08863v1 Announce Type: new Abstract: Recovering analytical solutions of physical fields from visual observations is a fundamental yet underexplored capability for AI-assisted scientific reasoning. We study visual-to-symbolic analytical solution inference (ViSA) for two-dimensional linear steady-state fields: given field visualizations (and first-order derivatives) plus minimal auxiliary metadata, the model must output a single executable SymPy expression […]
Entropy and diffusion characterize mutation accumulation and biological information loss
arXiv:2510.07265v2 Announce Type: replace Abstract: Aging is a universal consequence of life, yet researchers have identified no universal theme. This manuscript considers aging from the perspective of entropy, wherein things fall apart. We first examine biological information change as a mutational distance, analogous to physical distance. In this model, informational change over time is fitted […]
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
arXiv:2604.08865v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit assignment over long Chain-of-Thought (CoT) horizons and the prohibitive memory cost of the value model. While critic-free […]
ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
arXiv:2602.11354v2 Announce Type: replace Abstract: The literature has witnessed an emerging interest in AI agents for automated assessment of scientific papers. Existing benchmarks focus primarily on the computational aspect of this task, testing agents’ ability to reproduce or replicate research outcomes when having access to the code and data. This setting, while foundational, (1) fails […]
StaRPO: Stability-Augmented Reinforcement Policy Optimization
arXiv:2604.08905v1 Announce Type: new Abstract: Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization frameworks rely on final-answer correctness as feedback signals and rarely capture the internal logical structure of the reasoning process. Consequently, the models would generate fluent and semantically relevant responses […]
Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
arXiv:2404.10976v4 Announce Type: replace-cross Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches attempt to extend cooperation modelling to encompass behaviour similarities within groups, they commonly fall short in […]
Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
arXiv:2604.08931v1 Announce Type: new Abstract: Human cognitive development is shaped not only by individual effort but by structured social interaction, where role-based exchanges such as those between a tutor and a learner, enable solutions that neither could achieve alone. Inspired by these developmental principles, we ask the question whether a tutor-student multi-agent system can create […]