arXiv:2505.11881v2 Announce Type: replace-cross Abstract: Residual connections are pivotal for deep neural networks, enabling greater depth by mitigating vanishing gradients. However, in standard residual updates, the module’s output is directly added to the input stream. This can lead to updates…
arXiv:2509.20095v1 Announce Type: new Abstract: Swarm intelligence emerges from decentralised interactions among simple agents, enabling collective problem-solving. This study establishes a theoretical equivalence between pheromone-mediated aggregation in celeg and reinforcement learning (RL), demonstrating how stigmergic signals function as distributed reward…
arXiv:2506.19121v2 Announce Type: replace-cross Abstract: In robot imitation learning, policy performance is tightly coupled with the quality and composition of the demonstration data. Yet, developing a precise understanding of how individual demonstrations contribute to downstream outcomes – such as closed-loop…
arXiv:2509.20102v1 Announce Type: new Abstract: Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems. However, existing methods are often constrained to a single, fixed trade-off between competing objectives such as adversariality and realism. This yields…
arXiv:2508.05473v2 Announce Type: replace-cross Abstract: LLM-powered code generation has the potential to revolutionize creative coding endeavors, such as live-coding, by enabling users to focus on structural motifs over syntactic details. In such domains, when prompting an LLM, users may benefit…
arXiv:2509.20105v1 Announce Type: new Abstract: Large Language Models (LLMs) often struggle with maintaining coherent multi-step reasoning traces, particularly in tasks that require a structured logical flow. This work introduces a quantum-inspired approach to address the challenge by incorporating a fidelity-based…
arXiv:2509.20138v1 Announce Type: new Abstract: Using the Dafny verification system, we formally verify a range of minimax search algorithms, including variations with alpha-beta pruning and transposition tables. For depth-limited search with transposition tables, we introduce a witness-based correctness criterion and…
arXiv:2509.20107v1 Announce Type: cross Abstract: Hyperspectral imaging (HSI) captures spatial information along with dense spectral measurements across numerous narrow wavelength bands. This rich spectral content has the potential to facilitate robust robotic perception, particularly in environments with complex material compositions,…
arXiv:2509.20175v1 Announce Type: new Abstract: We present Federation of Agents (FoA), a distributed orchestration framework that transforms static multi-agent coordination into dynamic, capability-driven collaboration. FoA introduces Versioned Capability Vectors (VCVs): machine-readable profiles that make agent capabilities searchable through semantic embeddings,…
arXiv:2509.20166v1 Announce Type: cross Abstract: Today’s cyber defenders are overwhelmed by a deluge of security alerts, threat intelligence signals, and shifting business context, creating an urgent need for AI systems to enhance operational security work. While Large Language Models (LLMs)…
