DeepRead

Popular Tags

#VLM #agentic-RL #gui-agent #web-agent #LLM #VLA #computer-use #task-planning #manipulation #imitation-learning

Tag: agentic-RL

244 items with this tag.

Aug 20, 2026
Deep Research / Information-Seeking Agent 专题
Aug 20, 2026
Step-Level Credit Assignment：从 trajectory-level reward 反推步级监督
Aug 20, 2026
Self-Evolving and Self-Improving Agents: A Unified Survey of Evolution Targets, Feedback, Gating, and Safety
Aug 20, 2026
Computer-Use Agents: A Unified Survey of Models, Learning, Environments, Evaluation, and Deployment
Aug 20, 2026
Self-Initiated Fork：分支决策作为 GUI agent 的可学习动作
Aug 20, 2026
Quo Vadis, World Modeling? Towards Interactive World Proxies for Continually Improving Agents
Aug 20, 2026
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
Aug 20, 2026
StepReflect: Structured UI Transition Reflection for Mobile GUI Agents
- gui-agent
- agentic-RL
Aug 20, 2026
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
Aug 20, 2026
Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
Aug 20, 2026
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
- agentic-RL
- LLM
Aug 20, 2026
Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation
- gui-agent
- agentic-RL
Aug 20, 2026
Qwen-CUA: Native Computer Use for (almost) Everything
Aug 20, 2026
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
- agentic-RL
- LLM
Aug 20, 2026
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
Aug 20, 2026
The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents
- gui-agent
- agentic-RL
Aug 20, 2026
EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents
Aug 20, 2026
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
- agentic-RL
- world-model
Aug 20, 2026
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
Aug 20, 2026
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Aug 20, 2026
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
- agentic-RL
- LLM
Aug 20, 2026
Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
Aug 20, 2026
AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents
Aug 20, 2026
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
- agentic-RL
- LLM
Aug 20, 2026
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Aug 20, 2026
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
- deep-research
- agentic-RL
Aug 20, 2026
Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI
- LLM
- agentic-RL
Aug 20, 2026
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
- agentic-RL
- task-planning
Aug 20, 2026
AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
- agentic-RL
Aug 20, 2026
ACC: Compiling Agent Trajectories for Long-Context Training
- agentic-RL
- LLM
Aug 20, 2026
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Aug 20, 2026
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Aug 20, 2026
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Aug 20, 2026
Watch Before You Answer: Learning from Visually Grounded Post-Training
Aug 20, 2026
Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
- gui-agent
- agentic-RL
Aug 20, 2026
When Does Muon Help Agentic Reinforcement Learning?
- agentic-RL
- RL
Aug 20, 2026
ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning
- agentic-RL
- LLM
Aug 20, 2026
Teach it to stop, not just to click
Aug 20, 2026
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
Aug 20, 2026
Step-level Optimization for Efficient Computer-use Agents
Aug 20, 2026
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Aug 20, 2026
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Aug 20, 2026
SKILL-KD: Contrastive Skill Distillation for LLM Agents
Aug 20, 2026
SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents
- computer-use
- agentic-RL
Aug 20, 2026
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
Aug 20, 2026
Skill0: In-Context Agentic Reinforcement Learning for Skill Internalization
Aug 20, 2026
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Aug 20, 2026
Recursive Multi-Agent Systems
- LLM
- agentic-RL
Aug 20, 2026
Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember
Aug 20, 2026
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Aug 20, 2026
MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation
Aug 20, 2026
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation
Aug 20, 2026
Self-Evolving Agents with Anytime-Valid Certificates
- agentic-RL
- task-planning
Aug 20, 2026
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
- agentic-RL
- LLM
Aug 20, 2026
GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
Aug 20, 2026
SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
Aug 20, 2026
RAGEN-2: Reasoning Collapse in Agentic RL
Aug 20, 2026
Kimi K3: Open Frontier Intelligence
Aug 20, 2026
Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification
Aug 20, 2026
Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
Aug 20, 2026
HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents
- gui-agent
- agentic-RL
Aug 20, 2026
Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning
- agentic-RL
- VLM
Aug 20, 2026
Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training
- agentic-RL
- LLM
Aug 20, 2026
RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward
Aug 20, 2026
Dockerless: Environment-Free Program Verifier for Coding Agents
Aug 20, 2026
RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model
Aug 20, 2026
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
- agentic-RL
- web-agent
Aug 20, 2026
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Aug 20, 2026
ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
- agentic-RL
- task-planning
Aug 20, 2026
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
Aug 20, 2026
When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
- LLM
- agentic-RL
Aug 20, 2026
ReFAct: Empowering Multimodal Web Agents with Visual and Context Focusing
Aug 20, 2026
CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning
- VLM
- agentic-RL
Aug 20, 2026
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
- agentic-RL
Aug 20, 2026
FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification
- VLM
- agentic-RL
Aug 20, 2026
RAAS: LLM Agentic System Architecture Search with GRPO
- agentic-RL
- LLM
Aug 20, 2026
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
Aug 20, 2026
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
Aug 20, 2026
Qwen-AgentWorld: Language World Models for General Agents
Aug 20, 2026
CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning
Aug 20, 2026
Weak-to-Strong Generalization via Direct On-Policy Distillation
- LLM
- agentic-RL
Aug 20, 2026
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
- agentic-RL
- LLM
Aug 20, 2026
Heterogeneous Scientific Foundation Model Collaboration
Aug 20, 2026
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Aug 20, 2026
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
Aug 20, 2026
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
- VLM
- agentic-RL
Aug 20, 2026
AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents
Aug 20, 2026
On Safety Risks in Experience-Driven Self-Evolving Agents
Aug 20, 2026
Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
Aug 20, 2026
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Aug 20, 2026
Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process
Aug 20, 2026
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
Aug 20, 2026
Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning
- agentic-RL
- web-agent
Aug 20, 2026
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
- agentic-RL
- LLM
Aug 20, 2026
When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
Aug 20, 2026
Agentic Retoucher for Text-To-Image Generation
Aug 20, 2026
AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation
Aug 20, 2026
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
- agentic-RL
- web-agent
Aug 20, 2026
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
Aug 20, 2026
Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
Aug 20, 2026
Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
- computer-use
- agentic-RL
Aug 20, 2026
Xiaomi-GUI-0 Technical Report
- gui-agent
- agentic-RL
Aug 20, 2026
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
Aug 20, 2026
WebGym: Scaling Training Environments for Long-Horizon Visual Web Agents with Realistic Tasks
Aug 20, 2026
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
Aug 20, 2026
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
Aug 20, 2026
MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization
Aug 20, 2026
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Aug 20, 2026
Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
Aug 20, 2026
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
- agentic-RL
- VLM
Aug 20, 2026
AMusE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
Aug 20, 2026
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
- agentic-RL
- LLM
Aug 20, 2026
VisPlay: Self-Evolving Vision-Language Models
- agentic-RL
- VLM
Aug 20, 2026
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Aug 20, 2026
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Aug 20, 2026
VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning
Aug 20, 2026
LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding
Aug 20, 2026
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Aug 20, 2026
Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
Aug 20, 2026
When Vision Speaks for Sound
Aug 20, 2026
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
Aug 20, 2026
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
Aug 20, 2026
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Aug 20, 2026
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
- agentic-RL
- VLM
Aug 20, 2026
WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces
Aug 20, 2026
T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
- agentic-RL
- gui-agent
Aug 20, 2026
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
- agentic-RL
- task-planning
Aug 20, 2026
Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning
Aug 20, 2026
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Aug 20, 2026
SEVerA: Verified Synthesis of Self-Evolving Agents
- agentic-RL
- task-planning
Aug 20, 2026
Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation
Aug 20, 2026
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
- agentic-RL
- task-planning
Aug 20, 2026
PersonaVLM: Long-Term Personalized Multimodal LLMs
Aug 20, 2026
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
- agentic-RL
- LLM
Aug 20, 2026
HiconAgent: History Context-aware Policy Optimization for GUI Agents
Aug 20, 2026
Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
- agentic-RL
- RL
Aug 20, 2026
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
- agentic-RL
Aug 20, 2026
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
- agentic-RL
- LLM
Aug 20, 2026
SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
Aug 20, 2026
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
- VLM
- agentic-RL
Aug 20, 2026
Socratic-Geo: Synthetic Data Generation and Cross-Modal Geometric Reasoning via Multi-Agent Interaction
Aug 20, 2026
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
- gui-agent
- agentic-RL
Aug 20, 2026
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
Aug 20, 2026
SenseSearch: Empowering Vision-Language Models with High-Resolution Agentic Search-Reasoning via Reinforcement Learning
Aug 20, 2026
GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning
Aug 20, 2026
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
- gui-agent
- agentic-RL
Aug 20, 2026
GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots
- gui-agent
- agentic-RL
Aug 20, 2026
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
Aug 20, 2026
Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents
Aug 20, 2026
GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
Aug 20, 2026
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
Aug 20, 2026
Mem-W: Latent Memory-Native GUI Agents
Aug 20, 2026
LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning
Aug 20, 2026
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
- VLM
- agentic-RL
Aug 20, 2026
Harnessing LLM Agents with Skill Programs
Aug 20, 2026
EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval
Aug 20, 2026
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
- gui-agent
- agentic-RL
Aug 20, 2026
GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
- agentic-RL
- task-planning
Aug 20, 2026
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Aug 20, 2026
What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity
Aug 20, 2026
World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
Aug 20, 2026
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
- agentic-RL
- LLM
Aug 20, 2026
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
Aug 20, 2026
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
- agentic-RL
- LLM
Aug 20, 2026
WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
- agentic-RL
- web-agent
Aug 20, 2026
Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
Aug 20, 2026
Agentic Reward Modeling: Verifying GUI Agent via Online Proactive Interaction
Aug 20, 2026
ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents
Aug 20, 2026
When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training
- agentic-RL
- LLM
Aug 20, 2026
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Aug 20, 2026
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
Aug 20, 2026
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
- agentic-RL
- web-agent
Aug 20, 2026
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
- agentic-RL
- gui-agent
Aug 20, 2026
Process Rewards with Learned Reliability
- agentic-RL
- VLM
Aug 20, 2026
Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
Aug 20, 2026
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Aug 20, 2026
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Aug 20, 2026
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
- auto-research
- agentic-RL
Aug 20, 2026
Kimi K2.5: Visual Agentic Intelligence
Aug 20, 2026
Adaptive Milestone Reward for GUI Agents
Aug 20, 2026
Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
Aug 20, 2026
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
- agentic-RL
- LLM
Aug 20, 2026
WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
Aug 20, 2026
Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
Aug 20, 2026
AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
- computer-use
- agentic-RL
Aug 20, 2026
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
- gui-agent
- agentic-RL
Aug 20, 2026
Active Learners as Efficient PRP Rerankers
- LLM
- agentic-RL
Aug 20, 2026
ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
Aug 20, 2026
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- agentic-RL
- LLM
Aug 20, 2026
OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution
Aug 20, 2026
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- agentic-RL
- LLM
Aug 20, 2026
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
Aug 20, 2026
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
Aug 20, 2026
Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents
- gui-agent
- agentic-RL
Aug 20, 2026
AirNav: A Large-Scale Real-World UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions
Aug 20, 2026
VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning
Aug 20, 2026
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Aug 20, 2026
Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space
Aug 20, 2026
Go-Browse: Training Web Agents with Structured Exploration
- web-agent
- agentic-RL
Aug 20, 2026
GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks
Aug 20, 2026
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
- agentic-RL
- LLM
Aug 20, 2026
MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- LLM
- agentic-RL
Aug 20, 2026
Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
- web-agent
- agentic-RL
Aug 20, 2026
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
- agentic-RL
- LLM
Aug 20, 2026
FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents
Aug 20, 2026
MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
- gui-agent
- agentic-RL
Aug 20, 2026
Free Process Rewards without Process Labels
Aug 20, 2026
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Aug 20, 2026
ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments
Aug 20, 2026
BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism
- gui-agent
- agentic-RL
Aug 20, 2026
Audited Skill-Graph Self-Improvement for Agentic LLMs via Verifiable Rewards, Experience Synthesis, and Continual Memory
- agentic-RL
- task-planning
Aug 20, 2026
Reward Hacking in Reinforcement Learning
Aug 20, 2026
Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence
Aug 20, 2026
Large Language Model-Brained GUI Agents: A Survey
Aug 20, 2026
NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild
- web-agent
- agentic-RL
Aug 20, 2026
Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning
Aug 20, 2026
ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
- web-agent
- agentic-RL
Aug 20, 2026
Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?
- agentic-RL
- LLM
Aug 20, 2026
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
- web-agent
- agentic-RL
Aug 20, 2026
Grounding Computer Use Agents on Human Demonstrations
Aug 20, 2026
Scaling Agent Learning via Experience Synthesis
Aug 20, 2026
WebServ: A Browser-Server Environment for Efficient Training of Reinforcement Learning-based Web Agents at Scale
- web-agent
- agentic-RL
Aug 20, 2026
Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
- web-agent
- agentic-RL
Aug 20, 2026
Progress or Regress? Self-Improvement Reversal in Post-training
- agentic-RL
- LLM
Aug 20, 2026
Self-Initiated Fork：让 GUI agent 学会何时分支
Aug 20, 2026
Retrieval-Mediated Defense for Memory Misevolution
Aug 20, 2026
InSTA: Towards Internet-Scale Training For Agents
- web-agent
- agentic-RL
Aug 20, 2026
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
Aug 20, 2026
Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
Aug 20, 2026
Digi-Q: Learning Q-Value Functions for Training Device-Control Agents
Aug 20, 2026
EmbodiedBrain: Expanding Performance Boundaries of Task Planning for Embodied Intelligence
Aug 20, 2026
Counterfactual Probe Gating for Self-Evolution Steps
Aug 20, 2026
Scaling Long-Horizon LLM Agent via Context-Folding
Aug 20, 2026
CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent
Aug 20, 2026
Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails
- agentic-RL
- LLM
Aug 20, 2026
A Survey on Self-Evolution of Large Language Models
- LLM
- agentic-RL
Aug 20, 2026
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
Aug 20, 2026
Tree Search for LLM Agent Reinforcement Learning (Tree-GRPO)
- agentic-RL
- LLM
Jul 27, 2026
WebAgent 的 RL 训练与 Context 构造：两轴文献地图
Jul 27, 2026
WebAgent RL 训练方法对比：采样、输入输出与 Loss 公式逐篇核对
Jul 08, 2026
Web Agent 训练基础设施文章速览
Jul 03, 2026
2026-07-03-Autoresearch-AllTopics-Update
Jul 01, 2026
2026-07-01-Autoresearch-AllTopics-Update
Jun 23, 2026
WebGym 与 AsyncWebRL 阅读报告

Created with Quartz v4.5.2 © 2026

GitHub