Español

Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models
arXiv cs.AI Research & Papers
Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluatio…
arXiv cs.AI Research & Papers
What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Researc…
arXiv cs.AI Research & Papers
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World…
arXiv cs.AI Research & Papers
Superficial Beliefs in LLM Decision-Making
arXiv cs.AI Research & Papers
Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible…
arXiv cs.AI Research & Papers
Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?
arXiv cs.AI Research & Papers
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
arXiv cs.AI Research & Papers
WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds
arXiv cs.AI Research & Papers
TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition
arXiv cs.AI Research & Papers
What Spatial Memory Must Store: Occlusion as the Test for Language-Agent Memory
arXiv cs.AI Research & Papers
From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Con…
arXiv cs.AI Research & Papers
Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algori…
arXiv cs.AI Research & Papers
A complementary study on PlanGPT: Evaluation with defined Performance Metrics and compari…
arXiv cs.AI Research & Papers
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympi…
arXiv cs.AI Research & Papers
Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
arXiv cs.AI Research & Papers
Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents…
arXiv cs.AI Research & Papers
A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcem…
arXiv cs.AI Research & Papers
STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios
arXiv cs.AI Research & Papers
Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune
arXiv cs.AI Research & Papers
Belief-Space Control for Personalized Cancer Treatment via Active Inference
arXiv cs.AI Research & Papers
ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience
arXiv cs.AI Research & Papers
Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Lea…
arXiv cs.AI Research & Papers
Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Inte…
arXiv cs.AI Research & Papers
Culturally-Aware AI for Cross-Boundary Community Learning: Undergraduate Innovation at th…
arXiv cs.AI Research & Papers
Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
arXiv cs.AI Research & Papers
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
arXiv cs.AI Research & Papers
Large-scale semantic mapping of learner agency and autonomy reveals what measurement and …
arXiv cs.AI Research & Papers
Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise Evaluation
arXiv cs.AI Research & Papers
Moonshine: An Autonomous Mathematical Research Agent Centered on Conjecture Generation