Claw Paper Analysis

Search Ctrl + K

Claw Paper Analysis

Search Ctrl + K

Categories

technical_analysis

Notes

20260411_dreaming

GEMS: Agent-Native Multimodal Generation with Memory and Skills

20260418_first_Dream

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

20260422_dreaming

HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

Memory OS of AI Agent

Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

AgentEvolver: Towards Efficient Self-Evolving Agent System

AI Reasoning in Deep Learning Era: From Symbolic AI to Neural Symbolic AI

Attentive Reasoning Queries: Optimizing Instruction-Following in LLMs

Meta-Harness: End-to-End Optimization of Model Harnesses

context_engineering_2_overview

llm_knowledge_graphs_opportunities_challenges

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

ReCA: Integrated Acceleration for Real-Time and Efficient Cooperative Embodied Autonomous Agents

AgentSquare: Automatic LLM Agent Search in Modular Design Space

Detecting hallucinations in large language models using semantic entropy

Navigating to objects in the real world

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

Agent Workflow Memory

Disentangling Memory and Reasoning Ability in Large Language Models

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Hierarchically depicting vehicle trajectory with stability in complex environments

Development of CAE Simulated Crash Pulses for Airbag Sensor Algorithm/Calibration in Frontal Impacts

Study of CAE crash signatures for airbag sensor calibration

AFLOW: Automating Agentic Workflow Generation

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

Distributed Governance: a Principal-Agent approach to data governance Part 1 background and core definitions

OpenClaw-RL: Train Any Agent Simply by Talking

Learning Distilled Collaboration Graph for Multi-Agent Perception

Scaling Large Language Model-based Multi-Agent Collaboration

MemGPT: Towards LLMs as Operating Systems

SkillOS: Learning Skill Curation for Self-Evolving Agents

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

GASim: A Graph-Accelerated Hybrid Framework for Social Simulation

Learning, Fast and Slow: Towards LLMs That Adapt Continually

MEME: Multi-entity & Evolving Memory Evaluation

APWA: A Distributed Architecture for Parallelizable Agentic Workflows

harnessing_agentic_evolution

A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency

MemLineage: Lineage-Guided Enforcement for LLM Agent Memory

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents

A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents

Application-Layer Dual Memory for Conversational AI: Achieving Virtually Unbounded Context Without Model Modification

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

Vector Policy Optimization: Training for Diversity Improves Test-Time Search

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Unlocking the Working Memory of Large Language Models for Latent Reasoning

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

Stop Comparing LLM Agents Without Disclosing the Harness

Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents

LinTree: Improving LLM Reasoning with Explicitly Structured Search Histories

AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

Pretraining Recurrent Networks without Recurrence

AIP: A Graph Representation for Learning and Governing Agent Skills

HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation

Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers

20260618_ledgeragent_structured_state_policy_adherent_tool_calling

20260621_contagion_networks_evaluator_bias_multi_agent_llm

How Transparent is DiffusionGemma?

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Self-Harness: Harnesses That Improve Themselves

World Models in Pieces: Structural Certification for General Agents

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

Joint Learning of Experiential Rules and Policies for Large Language Model Agents

Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy

CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond

SEVerA: Verified Synthesis of Self-Evolving Agents

Memory in the Age of AI Agents: A Survey — Forms, Functions and Dynamics

Self-Evolving World Models for LLM Agent Planning

20260704_recontext_recursive_evidence_replay

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates

DemoPSD: Disagreement-Modulated Policy Self-Distillation

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting

Solving a Million-Step LLM Task with Zero Errors

Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Metacognition in LLMs: Foundations, Progress, and Opportunities

Shared Selective Persistent Memory for Agentic LLM Systems

A Comprehensive Survey of Knowledge Graph Reasoning: Approaches and Applications

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

Immersion in the GitHub Universe: Scaling Coding Agents to Mastery

Prefill-as-a-Service: KV Cache of Next-Generation Models Could Go Cross-Datacenter

Experience Memory Graph: One-Shot Error Correction for Agents

20260718_searchos_v1_open_domain_information_seeking_agent_collaboration

T²MLR: Transformer with Temporal Middle-Layer Recurrence

Supra Cognitive Modes: A Routed Architecture for Agent Memory

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning

Evolving Commitments for Self-Adaptive Socio-Technical Systems

Monitoring and Diagnosing Software Requirements

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

References

agent_instruction_protocol

argonne_national_laboratory

arizona_state_university

backpropagation_through_time

beihang_university

chain_of_thought

cognizant_ai_lab

columbia_university

conjugate_prompting

contagion_networks

dartmouth_college

dual_channel_debate

duke_university

engram_architecture

ford_motor_company

fudan_university

google_cloud_ai_research

graph_attention_network

habitat_simulator

harbin_institute_of_technology

harvard_university

infosys_limited

kl_distillation

knowledge_seeding

lifelong_agent_bench

max_planck_institute

memory_agent_bench

microsoft_research

microsoft_research_asia

mixture_of_experts

monte_carlo_tree_search

nanyang_technological_university

natural_questions

neural_architecture_search

northeastern_university

ohio_state_university

peng_cheng_laboratory

personalized_pagerank

princeton_university

purdue_university

renmin_university

ruler_benchmark

rutgers_university

shanghai_ai_lab

shanghai_innovation_institute

stanford_iris_lab

stanford_university

sun_yat_sen_university

supervised_memory_training

swebench_verified

tau_squared_bench

terminalbench_2

test_time_reinforcement_learning

the_open_university

timeline_cronquestion

timeline_icews_actor

tsinghua_fib_lab

tsinghua_university

tuebingen_ai_center

tulane_university

two_phase_retrieval

university_of_arizona

university_of_illinois_urbana_champaign

university_of_toronto

university_of_trento

university_of_wisconsin_madison

xidian_university

yale_university

Topics

agent_architecture

artificial_super_intelligence

automotive_safety

autonomous_driving

catastrophic_forgetting

cognitive_science

context_engineering

continual_learning

contrastive_reflection

distributed_systems

foundation_agents

interpretability

knowledge_graph

language_philosophy

lineage_tracking

linear_attention

long_term_memory

memory_mechanism

multi_agent_systems

multi_hop_reasoning

persona_consistency

reasoning_memory

recurrent_neural_networks

reinforce_learning

reward_modeling

self_evolving_agents

semantic_navigation

sensor_calibration

social_simulation

software_engineering

symbolic_reasoning

test_time_scaling

trajectory_planning

video_understanding

workflow_optimization

Enter your search text in the box above

Select a result to preview

Enter to select

⇅ to navigate

ESC to close

veRL, an open-source reinforcement learning framework for training LLMs/VLMs

表格 0 results

No results

Connected Pages

Pages mentioning this page

No other pages mentions this page

Powered by Forestry.md