Learning GenAI via SOTA Papers

Yun Wu

This podcast is focusing on sharing the papers on GenAI related topic, especially the SOTA (State of the Art) papers that are the foundations of GenAI work. It shows how these researches paved the way to the GenAI tools that we are using every day such as ChatGPT, Gemini, Claude Code etc.

  1. 3시간 전

    EP234: FATE fixes safe but useless AI agents

    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 architectural primitive for agents to autonomously balance safety and utility across long-horizon tool-use tasks.

    20분

  2. 19시간 전

    EP233: Fixing AI memory with backward chaining

    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 queries and retrieve missing intermediate facts for robust multi-hop reasoning.

    22분

  3. 1일 전

    EP232: Why AI agents lie to fit in

    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 Sovereignty Gap as foundational architectural constraints for designing robust and independent multi-agent reasoning topologies.

    20분

  4. 1일 전

    EP231: Amazon PIVOT solves the AI execution gap

    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 to trajectory optimization that enhances both constraint satisfaction and computational efficiency in autonomous systems.

    22분

  5. 2일 전

    EP230: DeepRefine fixes messy AI knowledge bases

    Title: DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Source: 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-fidelity external knowledge, which is essential for long-term agentic performance in knowledge-intensive tasks.

    23분

  6. 2일 전

    EP229: Ending the AI verbosity tax with LEAD

    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 models by introducing online, per-problem length estimation, paving the way for more efficient and scalable reasoning architectures.

    22분

  7. 3일 전

    EP228: Why self-evolving AI forgets basic tasks

    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 necessary architectural constraint for building stable, lifelong learning agents that can adapt to new tasks without catastrophic forgetting.

    23분

  8. 3일 전

    EP227: FlowAgent fixes the AI tool bottleneck

    Title: Tools as Continuous Flow for Evolving Agentic Reasoning Source: 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 significant shift in how agents execute long-horizon reasoning tasks.

    24분
모두 보기(234개)

소개

This podcast is focusing on sharing the papers on GenAI related topic, especially the SOTA (State of the Art) papers that are the foundations of GenAI work. It shows how these researches paved the way to the GenAI tools that we are using every day such as ChatGPT, Gemini, Claude Code etc.

정보