Learning GenAI via SOTA Papers - Explainer

Title: Mem-π: Adaptive Memory through Learning When and What to Generate Source: http://arxiv.org/abs/2605.21463v1 Summary: Mem-π presents a foundational shift in agent memory architectures by replacing static similarity-based retrieval with a dedicated generative model that produces context-specific guidance. This framework enables agents to dynamically adapt their memory usage, leading to substa...

Title: Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling Source: http://arxiv.org/abs/2605.21470v1 Summary: This paper introduces Agent Just-In-Time (JIT) compilation, a novel architectural primitive that transforms natural language task descriptions into optimized, executable code plans. It represents a significant breakthrough in agentic efficiency by replacing tradi...

Title: PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents Source: http://arxiv.org/abs/2605.19932v1 Summary: This work introduces 'context maps' as a novel architectural primitive for long-context agents, enabling them to cache and maintain structured orientation knowledge about recurring external datasets. By implementing a programmable cache policy for distilling and t...

Title: Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents Source: http://arxiv.org/abs/2605.19604v1 Summary: This work introduces a foundational architectural primitive for agents that replaces informal natural-language instructions with programmable, stateful runtime skills governed by hook policies and action schemas. This shift from prompting to executable state mac...

Title: A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits Source: http://arxiv.org/abs/2605.19944v1 Summary: This paper establishes fundamental theoretical bounds for LLM reasoning, proving that scaling physical layer depth is a non-negotiable requirement for out-of-distribution generalization that cannot be bypassed by scaling width. It also formalizes w...

Title: Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints Source: http://arxiv.org/abs/2605.19140v1 Summary: This research provides the first finite-sample guarantee for neural Q-learning in decentralized multi-agent settings, a foundational breakthrough for reliable agentic workflow learning. By formalizing handoffs as interface-constrained SMDPs, it enables p...

Title: Generating Pretraining Tokens from Organic Data for Data-Bound Scaling Source: http://arxiv.org/abs/2605.17849v1 Summary: This work addresses the transition of LLM pretraining into data-bound regimes by introducing a synthetic data generation framework that maximizes the utility of limited organic datasets. It represents a significant breakthrough in scaling laws, demonstrating how to unloc...

Title: EXG: Self-Evolving Agents with Experience Graphs Source: http://arxiv.org/abs/2605.17721v1 Summary: This paper introduces the first experience graph framework for self-evolving agents, providing a structured relational representation for successes and failures that enables real-time experience reuse. It establishes a principled foundation for scalable agent behavior by allowing behaviorally...

Title: Parallelizing Counterfactual Regret MinimizationSource: http://arxiv.org/abs/2605.14277v1 Summary: This work introduces a generalized framework that reframes counterfactual regret minimization as linear algebra operations, allowing for massive parallelization on modern hardware. By achieving a four-order-of-magnitude speedup, it provides a foundational efficiency breakthrough for the reason...

Title: Orchard: An Open-Source Agentic Modeling Framework Source: http://arxiv.org/abs/2605.15040v1 Summary: Orchard provides a scalable open-source framework for agentic modeling, introducing reusable environment primitives and training recipes that enable LLMs to achieve state-of-the-art performance on complex tasks. It addresses critical gaps in agent infrastructure by standardizing sandbox man...

Title: Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent SystemsSource: http://arxiv.org/abs/2605.14892v1 Summary: This work introduces the LIFE progression framework, which formally characterizes the causal dependencies between agent foundation, collaboration, failure attribution, and autonomous self-evolution. It establishes...

Title: Agentifying Patient Dynamics within LLMs through Interacting with Clinical World ModelSource: http://arxiv.org/abs/2605.14723v1 Summary: This work presents a novel world-model-augmented agentic reasoning loop that utilizes a 'propose-simulate-refine' workflow to ground LLM decisions in action-conditioned dynamics. It demonstrates how integrating world models with agentic reinforceme...

Title: MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning Source: http://arxiv.org/abs/2605.13037v1 Summary: MAP proposes a paradigm shift for interactive agents by establishing environmental understanding through structured cognitive mapping before task execution. This approach overcomes the epistemic bottlenecks and inefficient failure cycles inherent in traditional reacti...

Title: Harnessing Agentic Evolution Source: http://arxiv.org/abs/2605.13821v1 Summary: AEvo introduces a meta-editing framework that treats the evolution context as a process-level state, allowing agents to iteratively refine their own procedures. This shifts agentic evolution from rigid hand-designed loops to a unified interface for actionable, long-horizon self-improvement.

Title: SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory Source: http://arxiv.org/abs/2605.12061v1 Summary: SAGE introduces a self-evolving graph-memory engine that couples a memory writer with a Graph Foundation Model-based reader to create a dynamic, self-improving long-term memory substrate. This framework is foundational for its architectural move beyond...

Title: On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment Source: http://arxiv.org/abs/2605.11882v1 Summary: FATE establishes a foundational framework for on-policy self-evolution by transforming agentic failure trajectories into high-density repair supervision without human demonstrations. By employing Pareto-Front Policy Optimization, it provides a scalable architectu...

Title: Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems Source: http://arxiv.org/abs/2605.12213v1 Summary: This paper presents Goal-Mem, a framework that employs backward chaining and Natural Language Logic to create a goal-oriented reasoning loop for agentic memory systems. It provides a foundational advancement in how agents can systematically decompose complex...

Title: The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions Source: http://arxiv.org/abs/2605.10698v1 Summary: This study formalizes the 'Bystander Effect' in multi-agent systems, identifying a critical failure mode where agents subjugate independent reasoning to social compliance. It introduces the Interaction Depth Limit and Sovereign...

Title: PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement Source: http://arxiv.org/abs/2605.11225v1 Summary: PIVOT introduces a novel self-supervised framework that treats agent trajectories as optimizable objects refined through iterative environment feedback, bridging the gap between high-level planning and execution. This methodology establishes a principled approach...

Title: DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement LearningSource: http://arxiv.org/abs/2605.10488v1 Summary: DeepRefine establishes a general reinforcement learning framework for the autonomous refinement of agent-compiled knowledge bases using abductive diagnosis and a novel Gain-Beyond-Draft reward. It provides a foundational reasoning loop for maintaining persistent, high...

Title: LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models Source: http://arxiv.org/abs/2605.09806v1 Summary:LEAD establishes a foundational reinforcement learning mechanism for reasoning models that dynamically calibrates the balance between correctness and verbosity at each training step. It solves the critical issue of 'overthinking' in modern reasoning model...

Title: Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation Source: http://arxiv.org/abs/2605.09315v1 Summary: This paper introduces the 'capability erosion' framework to quantify how autonomous self-evolution can degrade an agent's prior knowledge across workflows and models. It proposes Capability-Preserving Evolution (CPE) as a nec...

Title: Tools as Continuous Flow for Evolving Agentic ReasoningSource: http://arxiv.org/abs/2605.07339v1 Summary: FlowAgent reconceptualizes agentic reasoning by replacing discrete, step-wise tool orchestration with continuous trajectory generation using conditional flow matching. This foundational framework provides theoretical guarantees for error attenuation and global planning, representing a s...

Title: Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models Source: http://arxiv.org/abs/2605.07721v1 Summary:This paper introduces a novel architectural primitive that decouples reasoning depth from memory consumption in looped language models, enabling constant-memory iterative reasoning. By sharing a single KV cache across loops via a learnable gating me...

Title: Logic-Regularized Verifier Elicits Reasoning from LLMs Source: http://arxiv.org/abs/2605.05893v1 Summary: This work presents a novel reasoning framework that uses logical consistency rules to regularize unsupervised verifiers, eliminating the need for expensive supervised datasets. By treating verification as a binary latent variable problem, it achieves performance comparable to supervised...