#Computer Science
Latest news articles tagged with "Computer Science". Follow the timeline of events, related topics, and entities.
Articles (17)
-
🇺🇸 Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents
[USA]
arXiv:2602.22402v1 Announce Type: cross Abstract: As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions, codeba...
Related: #Artificial Intelligence, #Software Engineering -
🇺🇸 Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks
[USA]
arXiv:2602.07009v1 Announce Type: cross Abstract: Artificial neural networks achieve strong performance on benchmark tasks but remain fundamentally brittle under perturbations, limiting their deploym...
Related: #Artificial Intelligence, #Biomimicry -
🇺🇸 Intermediate Results on the Complexity of STRIPS$_{1}^{1}$
[USA]
arXiv:2602.08708v1 Announce Type: new Abstract: This paper is based on Bylander's results on the computational complexity of propositional STRIPS planning. He showed that when only ground literals ar...
Related: #Computational Complexity, #Artificial Intelligence -
🇺🇸 The Vibe-Automation of Automation: A Proactive Education Framework for Computer Science in the Age of Generative AI
[USA]
arXiv:2602.08295v1 Announce Type: new Abstract: The emergence of generative artificial intelligence (GenAI) represents not an incremental technological advance but a qualitative epistemological shift...
Related: #Education, #Artificial Intelligence -
🇺🇸 G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design
[USA]
arXiv:2602.08253v1 Announce Type: new Abstract: While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing approaches typically formulate AHD around ...
Related: #Artificial Intelligence, #Optimization -
🇺🇸 Circuit Representations of Random Forests with Applications to XAI
[USA]
arXiv:2602.08362v1 Announce Type: new Abstract: We make three contributions in this paper. First, we present an approach for compiling a random forest classifier into a set of circuits, where each ci...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents
[USA]
arXiv:2602.07359v1 Announce Type: new Abstract: Deep research agents have emerged as powerful tools for automating complex intellectual tasks through multi-step reasoning and web-based information se...
Related: #Artificial Intelligence, #Efficiency -
🇺🇸 Learning to Continually Learn via Meta-learning Agentic Memory Designs
[USA]
arXiv:2602.07755v1 Announce Type: new Abstract: The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adap...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Free(): Learning to Forget in Malloc-Only Reasoning Models
[USA]
arXiv:2602.08030v1 Announce Type: new Abstract: Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade perfor...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis
[USA]
arXiv:2602.08276v1 Announce Type: new Abstract: Current research on large language model (LLM) agents is fragmented: discussions of conceptual frameworks and methodological principles are frequently ...
Related: #Artificial Intelligence, #Technical Research -
🇺🇸 Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI
[USA]
arXiv:2602.06934v1 Announce Type: cross Abstract: Grassroots Logic Programs (GLP) is a concurrent logic programming language with variables partitioned into paired \emph{readers} and \emph{writers}, ...
Related: #Artificial Intelligence, #Concurrent Programming -
🇺🇸 Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristics
[USA]
arXiv:2508.12840v4 Announce Type: replace Abstract: Multi-agent Epistemic Planning (MEP) is an autonomous planning framework for reasoning about both the physical world and the beliefs of agents, wit...
Related: #Artificial Intelligence, #Robotics -
🇺🇸 Intrinsic Stability Limits of Autoregressive Reasoning: Structural Consequences for Long-Horizon Execution
[USA]
arXiv:2602.06413v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their performance often deteriorates sharply in long-horizon tasks, exh...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
[USA]
arXiv:2602.06822v1 Announce Type: new Abstract: Large foundation models (LFMs) achieve strong performance through scaling, yet current structural pruning methods derive fixed pruning decisions during...
Related: #Artificial Intelligence, #Model Optimization -
🇺🇸 Di3PO -- Diptych Diffusion DPO for Targeted Improvements in Image
[USA]
arXiv:2602.06355v1 Announce Type: cross Abstract: Existing methods for preference tuning of text-to-image (T2I) diffusion models often rely on computationally expensive generation steps to create pos...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering
[USA]
arXiv:2602.06142v1 Announce Type: cross Abstract: The phase ordering problem has been a long-standing challenge since the late 1970s, yet it remains an open problem due to having a vast optimization ...
Related: #Software Optimization, #Compilers -
🇺🇸 Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
[USA]
arXiv:2602.05605v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) incur prohibitive computational costs due to the quadratic scaling of self-attention. Existing pruning methods fail to ...
Related: #Artificial Intelligence, #Hardware Optimization