Learning GenAI via SOTA Papers - Explainer

Title: HaM-World: Soft-Hamiltonian World Models with Selective Memory for PlanningSource: http://arxiv.org/abs/2605.05951v1 Summary: This paper introduces a foundational architectural primitive for world models by combining Hamiltonian geometric structures with Mamba-based selective memory to stabilize long-horizon planning. It provides agents with a structured latent state for dynamics, rewards,...

Title: Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation Source: http://arxiv.org/abs/2605.05007v1 Summary: This paper introduces a novel orchestration policy that jointly optimizes task decomposition and agent routing, establishing a new frontier for efficiency and accuracy in multi-agent systems. It moves beyond rigid workflows by learning selective delegation from RL trajectori...

Title: Gyan: An Explainable Neuro-Symbolic Language Model Source: http://arxiv.org/abs/2605.04759v1 Summary: Gyan proposes a breakthrough non-transformer architecture that decouples language modeling from knowledge representation to eliminate hallucinations and drastically reduce compute requirements. It introduces a neuro-symbolic framework that mimics human compositional context, offering a more...

Title: ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical ForgettingSource: http://arxiv.org/abs/2605.03804v1 Summary: ScrapMem introduces a novel on-device memory architecture for agents that employs bio-inspired 'Optical Forgetting' to maintain long-term multimodal context with extreme storage efficiency. It establishes a foundational framework for per...

Title: Parallel Prefix Verification for Speculative Generation Source: http://arxiv.org/abs/2605.04263v1 Summary: This paper introduces PARSE, a novel speculative generation primitive that enables semantic-level verification across multiple prefixes in a single forward pass. By eliminating sequential bottlenecks in speculative decoding, it achieves up to 4.3x throughput gains, representing a major...

Title: Parallel Prefix Verification for Speculative Generation Source: http://arxiv.org/abs/2605.04263v1 Summary: This paper introduces PARSE, a novel speculative generation primitive that enables semantic-level verification across multiple prefixes in a single forward pass. By eliminating sequential bottlenecks in speculative decoding, it achieves up to 4.3x throughput gains, representing a major...

Title: OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories Source: http://arxiv.org/abs/2605.04036v1 Summary: This paper establishes a high-efficiency paradigm for training frontier search agents using only supervised fine-tuning on high-quality synthesized trajectories, challenging resource-intensive industry standards. It provides a foundational m...

Title: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation Source: http://arxiv.org/abs/2605.04128v1 Summary:JoyAI-Image establishes a new foundational architecture for multimodal agents by tightly coupling a spatially enhanced MLLM with a Multimodal Diffusion Transformer through a shared interface. This unified primitive enables a bidirectional feedback loop between vi...

Title: The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure Source: http://arxiv.org/abs/2605.02398v1 Summary: This work identifies the 'Compliance Trap,' a fundamental failure mode where alignment constraints cause catastrophic metacognitive collapse in frontier models under pressure. It provides a foundational framework for understa...

Title: MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory Source: http://arxiv.org/abs/2605.03228v1 Summary: MAGE introduces the 'shadow memory' abstraction, a novel defensive framework that maintains a safety-focused agentic memory to counter long-horizon threats. It establishes a new paradigm for agentic safety by enabling models to proactively assess risk acros...

Title: GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing Source: http://arxiv.org/abs/2605.02489v1 Summary: GRAIL introduces a novel SLM-enhanced indexing and resonance framework that solves the foundational scaling bottleneck of agent discovery in large-scale ecosystems. By achieving a 79x reduction in latency, it provides a critical arch...

Title: ARISE: A Repository-level Graph Representation and Toolset for Agentic Fault Localization and Program Repair Source: http://arxiv.org/abs/2605.03117v1 Summary: ARISE introduces a multi-granularity program graph and data-flow slicing as a first-class, queryable agent primitive for repository-level fault localization. This architectural primitive significantly improves agentic reasoning for c...

Title: Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation Source: http://arxiv.org/abs/2605.01750v1 Summary: This research identifies 'dynamic grounding' as a foundational and critical axis for multi-agent coordination, revealing it as a primary bottleneck that exceeds individual reasoning or simple information exchange. It proposes a nov...

Title: Sheaf-Theoretic Planning: A Categorical Foundation for Resilient Multi-Agent Autonomous SystemsSource: http://arxiv.org/abs/2605.01879v1 Summary: This paper introduces Sheaf-Theoretic Planning (STP) as a transformative architectural primitive that replaces traditional monolithic logical models with a foundation in topos theory and sheaf semantics. It establishes a novel mathematical framewo...

Title: SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning Source: http://arxiv.org/abs/2605.01489v1 Summary: Introduces a novel paradigm for automated data construction to scale agentic reasoning, achieving state-of-the-art results with an 8B foundation model. It bridges the gap in frontier science by synthesizing conceptual and computational tasks grounded in academic e...

Title: Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks Source: http://arxiv.org/abs/2605.01293v1 Summary: Proposes a neuro-symbolic framework that lifts interaction traces into modular, logic-grounded programs to solve long-horizon planning challenges. This paradigm enables agents to induce skills from few-shot examples and adapt to...

Title: SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters Source: http://arxiv.org/abs/2605.00528v1 Summary: SAGA represents a foundational breakthrough in agentic AI systems by transitioning from request-level to workflow-atomic scheduling for GPU inference. By capturing and optimizing for the chained structure of agentic tasks, it significantly reduces latency and resource o...

Title: Position: agentic AI orchestration should be Bayes-consistent Source: http://arxiv.org/abs/2605.00742v1 Summary: This position paper establishes a novel theoretical foundation for agentic AI by arguing that the orchestration layer must be Bayes-consistent to handle uncertainty in complex decision-making. It provides a formal framework for belief-updating and utility-aware action selection,...

Title: PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations Source: http://arxiv.org/abs/2604.27472v1 Summary: PRTS establishes a new foundation model paradigm by reformulating VLA pretraining as Goal-Conditioned Reinforcement Learning to learn a unified goal-reachability embedding space. This architectural primitive bridges the gap between semantic reasoning and physical...

Title: ObjectGraph: From Document Injection to Knowledge Traversal -- A Native File Format for the Agentic Era Source: http://arxiv.org/abs/2604.27820v1 Summary: ObjectGraph introduces a new native file format that reconceives linear documents as typed knowledge graphs specifically optimized for autonomous agent traversal rather than human reading. This foundational shift in data representation ad...

Title: End-to-end autonomous scientific discovery on a real optical platform Source: http://arxiv.org/abs/2604.27092v1 Summary: This work marks a milestone by demonstrating the first AI agentic system to autonomously identify and experimentally validate a previously unreported physical mechanism. It introduces a novel dual-layer architecture and Meta-Trace memory to maintain stable research trajec...

Title: AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents Source: http://arxiv.org/abs/2604.26522v1 Summary: This framework introduces a principled neuro-symbolic architecture that addresses systemic failures in compositional generalization within LLM-based agents. It integrates dynamic causal program graphs, inductive logic programming, and neural theorem...

Title: Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital Source: http://arxiv.org/abs/2604.26091v1 Summary: This paper identifies the "operating layer"—comprising prompt compilation, typed controls, and execution guards—as the critical architectural framework for ensuring agentic reliability in high-stakes environments. It provides a foundational blueprint for...

Title: ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents Source: http://arxiv.org/abs/2604.25849v1 Summary: ADEMA establishes a foundational architecture for long-horizon agentic reasoning by introducing explicit epistemic bookkeeping and knowledge-state orchestration to prevent information drift. This framework provides a new primitive for com...

Title: Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model Source: http://arxiv.org/abs/2604.24809v1 Summary: This paper introduces a hybrid architecture that alternates linear-time spectral operators with transformer layers, providing a formal proof that such 'spectral memory' can match the expressiveness of full self-attention. It demonstrates a significant breakthro...