Bounded knowledge map
Recent connections
Explicit wiki links among recent Agents entries.
90 nodes · 4 links. The server bounds this neighbourhood, so the browser never downloads or simulates the complete wiki graph.
90 nodes · 4 links shown. Hover or focus to isolate neighbours; select a node to open its source entry.
Linked entries
4 shownProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents→MemTrace: State-Consistent Memory for Long-Horizon Coding Agents
New paper from the team at Sakana AI: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS) How do we keep improving AI whe…→Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through …
Agents
90 shownNew paper from the team at Sakana AI: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS) How do we keep improving AI whe…2Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through …2Recursive Self-Improvement through Multi-Agent Self-Supervision2ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents1MemTrace: State-Consistent Memory for Long-Horizon Coding Agents1JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World ModelsLarge Language Models, Machine-Assisted Cultural Analytics, and the Agentic TurnCB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual BanditsBeyond the Snowflakes: Disentangling Weather Effects from Confounding Meta-Factors in LiDAR Object DetectionCan Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level LabelsForgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM AgentsThe value of information and the emergence of communication in evolved e-puck robotsWhen Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent WorkflowsSWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent TrajectoriesData-Driven Stochastic Optimal Control in Reproducing Kernel Hilbert SpacesInfinitesimal Operator World Models: Finite-Sample Guarantees for Offline Reinforcement LearningWeb$hell: A Unified Interface for Agentic Web AccessSustainable Cloud-Fog-Edge Systems for Smart Buildings: Algorithmic Adaptation under Memory Constraints and Dynamic Orchestration StrategiesMapless, Stabilizing, and Anti-Stuck Flipper Control for Articulated Tracked RobotsReflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level OverfittingPrediction-Informed Landing Window Planning for UAV Landing on USV in High Sea StatesAgent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market AnalysisARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative SimulationSynAct: Synergistic Active Feedback Learning for LLM AgentsMeta-Reflective Evolution Effectively Improves Production AI SystemsScaling Empowered AgentsPACT: Privileged Trace Co-Training for Multi-Turn Tool-Use AgentsMARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoSWork2Skill: Capturing Human GUI Experience for Reusable Agent Skill InductionSEEDS: Preview-Guided Evidence Admission for Search AgentsTelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded ExplainabilityHumanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent LimitsFly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical FeedbackX-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service EcosystemsDoes Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?Cubic Spline Interpolation for Smooth Trajectory Generation in Autonomous Motion SystemsCo-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull RequestsAgentic Large Language ModelsKnow What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop LearningCompetence-Aware Orchestration for LLM-Based Multi-Agent SystemsIncremental Retrieval-Augmented Generation for Human-in-the-Loop Decision SupportCollective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human DriversA Multi-Agent LLM System for Automated Tuning of Specialized Neural Network ModelsRecurrent Harness for Agentic Continual LearningDusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of peo…The Top AI Papers of the Week (October 5 - October 11): - VERA - HERMES - CorpusMap - VeriHarness - Sharpening Tax - Harness Learning - Mult…One of the biggest historical bottlenecks for training specialized models has been curating ground-truth. This is typically a very labor int…Why AI agents might not be right for you“The field of artificial life is a very long-term bet on intelligence.” 🐙 Our former intern Akarsh Kumar recently joined @MLStreetTalk to d…AI agent makers are promising privacy — will they deliver?good framing from @ch3nweiii - a lot of agent steps are yes/no calls, not generation Jev answers those as typed questions with calibrated pr…Satya is spot on. The interesting engineering problem isn’t just making models behave, it’s building systems that don’t need to trust them i…'a corollary is that information about product quality will become more important and impactful' This feels like the next evolution of SEO/A…Wild MISSINGNO. appeared! A coding and agentic reasoning model that is highly token efficient, free for a limited time on Nous Portal Try it…Is anyone running Qwen3.8 Flash Next with a 1M context?Nice paper on agent memory. It explores an effective routing mechanism for memory in agents. The overall finding is that you want a separate…Beyond Type-checking: Towards Holistic Evaluation of Formal Specification GenerationInstinct was the buzziest AI agent around — can it survive Muse?MAPF-World: Action World Model for Multi-Agent Path FindingRFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip DesignAgentEvolver: System-Wide Self-Evolution Through Task ExecutionChronos Enables Code Agents to Reason over Software EvolutionLEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphsgoing rate for this role is between 5-50m comp package btw at the frontier agent labsAttention when you needEvoSim: Learning to Model, Modeling to LearnMiMo-V2.6: Scaling Reinforcement Learning Towards Self-ImprovementWhat happens when a table contains tables? Usually, a mess. With LlamaParse, it comes out clean. Doc of the Week: Micron’s latest earnings d…Simultaneous Computation with Multiple Prioritizations in Multi-Agent Motion PlanningDeltaReplay: Task-Relative Memory Reuse for Mobile GUI AgentsToday, we are announcing LlamaIndex. It is here: https://llamaindex.aiAutonomous thermodynamic cycles via robotic mobility and sensingWho Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving AgentsBeyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoorsi'm pulling out my suit for this Huge shoutout to @imaanxsultan and everyone else for organizing!SuperNav: An Agentic Navigation System for Any Task in Any SceneForms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent SystemiAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary DomainsAgentFly: Scaling Agentic Reinforcement Learning with Unified Resource SystemSpatial Pattern Formation from Multi-Agent Learning in Public Goods DilemmasThese days, you can pretty much solve any task by defining an eval and hillclimbing over it, instead of directly defining the deterministic/…OneSearch-VL: Unified Multimodal Deep Research Agent for Image and VideoOpen-ended Scientific Discovery with Possibilistic ReasoningHarness Evolution Hits a Ceiling: When Weight Training Should BeginSim-to-Real RL for ASVs using SysIDEvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program EvolutionLM Studio 0.4.26 is out now! • ⚡️ `/v1/systemone` and `/v1/decisions` APIs • 👾 Coexistence with Bionic • 🎨 UI updates and bug fixes Yes, y…PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous DrivingIntervention anchors and scientific verification in synthetic vascular predictive representationsPrompts versus Rules: Auditing and Controlling Speech Naturalness Behaviors in Voice User Simulators