| 20260414_gems_agent_native_multimodal_generation_memory_skills | GEMS: Agent-Native Multimodal Generation with Memory and Skills | agent_architecture, multimodal, memory_mechanism, long_term_memory, llm |
| 20260419_memskill_learning_evolving_memory_skills | MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents | self_evolving_agents, memory_mechanism, agent_architecture, llm, long_term_memory |
| 20260422_hipporag_neurobiologically_inspired_long_term_memory | HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models | rag, knowledge_graph, multi_hop_reasoning, neuro_science, memory_mechanism |
| 20260422_llm_semantic_reasoners_not_symbolic_reasoners | Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners | llm, reasoning, cognitive_science, language_philosophy |
| 20260422_memory_os_of_ai_agent | Memory OS of AI Agent | agent_architecture, memory_mechanism, long_term_memory, context_engineering |
| 20260422_multimodal_agent_long_term_memory | Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory | agent_architecture, multimodal, memory_mechanism, long_term_memory, video_understanding |
| 20260423_agentevolver_self_evolving_agent | AgentEvolver: Towards Efficient Self-Evolving Agent System | agent_architecture, reinforce_learning, llm, reasoning |
| 20260423_ai_reasoning_deep_learning_symbolic_neural | AI Reasoning in Deep Learning Era: From Symbolic AI to Neural Symbolic AI | reasoning, symbolic_reasoning, llm, knowledge_graph, neuro_science, cognitive_science |
| 20260423_attentive_reasoning_queries | Attentive Reasoning Queries: Optimizing Instruction-Following in LLMs | llm, agent_architecture, reasoning, cognitive_science, context_engineering |
| 20260423_meta_harness_end_to_end_optimization | Meta-Harness: End-to-End Optimization of Model Harnesses | context_engineering, agent_architecture, llm, reasoning, rag |
| 20260424_context_engineering_2_overview | context_engineering_2_overview | context_engineering, llm, agent_architecture, reasoning |
| 20260424_llm_knowledge_graphs_opportunities_challenges | llm_knowledge_graphs_opportunities_challenges | knowledge_graph, llm, rag, reasoning |
| 20260425_chain_of_thought_prompting_elicits_reasoning | Chain-of-Thought Prompting Elicits Reasoning in Large Language Models | llm, reasoning, cognitive_science, context_engineering, multi_hop_reasoning |
| 20260425_reca_integrated_acceleration_cooperative_embodied_agents | ReCA: Integrated Acceleration for Real-Time and Efficient Cooperative Embodied Autonomous Agents | llm, agent_architecture, memory_mechanism, embodied_ai, multi_hop_reasoning |
| 20260427_agentsquare_automatic_llm_agent_search | AgentSquare: Automatic LLM Agent Search in Modular Design Space | agent_architecture, llm, reasoning, memory_mechanism, reinforce_learning |
| 20260427_detecting_hallucinations_semantic_entropy | Detecting hallucinations in large language models using semantic entropy | llm, reasoning, agent_architecture, memory_mechanism, reinforce_learning |
| 20260428_navigating_to_objects_in_the_real_world | Navigating to objects in the real world | embodied_ai, reinforce_learning, sim_to_real, semantic_navigation |
| 20260428_rubrics_as_rewards | Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains | reinforce_learning, llm, reasoning, reward_modeling |
| 20260429_agent_workflow_memory | Agent Workflow Memory | agent_architecture, memory_mechanism, llm, gui_agent, long_term_memory, cognitive_science |
| 20260429_disentangling_memory_reasoning_llm | Disentangling Memory and Reasoning Ability in Large Language Models | memory_mechanism, reasoning, llm, multi_hop_reasoning, chain_of_thought, cognitive_science |
| 20260430_catastrophic_forgetting_implicit_inference | Understanding Catastrophic Forgetting in Language Models via Implicit Inference | catastrophic_forgetting, llm, memory_mechanism, reasoning, context_engineering |
| 20260430_hallucination_survey_llm | A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions | hallucination, llm, survey, rag, reinforce_learning |
| 20260430_hierarchically_depicting_vehicle_trajectory | Hierarchically depicting vehicle trajectory with stability in complex environments | robotics, autonomous_driving, trajectory_planning, embodied_ai |
| 20260502_cae_crash_pulses_airbag_sensor_calibration_frontal_impacts | Development of CAE Simulated Crash Pulses for Airbag Sensor Algorithm/Calibration in Frontal Impacts | sensor_calibration, sim_to_real, automotive_safety |
| 20260502_study_cae_crash_signatures_airbag_sensor_calibration | Study of CAE crash signatures for airbag sensor calibration | sensor_calibration, sim_to_real, automotive_safety |
| 20260503_aflow_automating_agentic_workflow_generation | AFLOW: Automating Agentic Workflow Generation | agent_architecture, llm, reasoning, workflow_optimization |
| 20260504_reasoningbank_scaling_agent_self_evolving_reasoning_memory | ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory | self_evolving_agents, reasoning_memory, test_time_scaling, agent_architecture, memory_mechanism |
| 20260504_self_evolving_agents_survey_asi | A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence | self_evolving_agents, artificial_super_intelligence, survey, agent_architecture, memory_mechanism |
| 20260506_distributed_governance_principal_agent_data_governance | Distributed Governance: a Principal-Agent approach to data governance Part 1 background and core definitions | data_governance, distributed_systems, digital_identity, ontology |
| 20260506_openclaw_rl_train_any_agent_simply_by_talking | OpenClaw-RL: Train Any Agent Simply by Talking | reinforce_learning, agent_architecture, llm, self_evolving_agents, reasoning |
| 20260507_learning_distilled_collaboration_graph_multi_agent_perception | Learning Distilled Collaboration Graph for Multi-Agent Perception | autonomous_driving, distributed_systems, embodied_ai, robotics |
| 20260507_scaling_large_language_model_multi_agent_collaboration | Scaling Large Language Model-based Multi-Agent Collaboration | llm, agent_architecture, workflow_optimization, distributed_systems |
| 20260508_memgpt_towards_llms_as_operating_systems | MemGPT: Towards LLMs as Operating Systems | llm, memory_mechanism, agent_architecture, long_term_memory, context_engineering |
| 20260509_skillos_learning_skill_curation_self_evolving_agents | SkillOS: Learning Skill Curation for Self-Evolving Agents | agent_architecture, memory_mechanism, reinforce_learning, self_evolving_agents, skill_curation |
| 20260511_rl_long_horizon_reasoning_llm_expressiveness | Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key | reinforce_learning, reasoning, llm, test_time_scaling, symbolic_reasoning |
| 20260512_gasim_graph_accelerated_hybrid_social_simulation | GASim: A Graph-Accelerated Hybrid Framework for Social Simulation | agent_architecture, memory_mechanism, knowledge_graph, llm, multi_agent_systems |
| 20260512_learning_fast_slow_llms_adapt_continually | Learning, Fast and Slow: Towards LLMs That Adapt Continually | catastrophic_forgetting, continual_learning, memory_mechanism, reinforce_learning, llm |
| 20260512_meme_multi_entity_evolving_memory_evaluation | MEME: Multi-entity & Evolving Memory Evaluation | memory_mechanism, long_term_memory, agent_architecture, llm, reasoning, evaluation |
| 20260515_apwa_parallelizable_agentic_workflows | APWA: A Distributed Architecture for Parallelizable Agentic Workflows | multi_agent_systems, agent_architecture, distributed_systems, workflow_optimization, reasoning, llm |
| 20260515_harnessing_agentic_evolution | harnessing_agentic_evolution | agent_architecture, self_evolving_agents, reasoning, memory_mechanism, reinforce_learning, workflow_optimization |
| 20260517_heterogeneous_temporal_memory_governance_llm_persona | A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency | memory_mechanism, llm, long_term_memory, rag, reasoning, persona_consistency |
| 20260518_memlineage_lineage_guided_llm_agent_memory | MemLineage: Lineage-Guided Enforcement for LLM Agent Memory | memory_mechanism, agent_architecture, llm, agent_security, lineage_tracking |
| 20260520_amr_sd_token_level_credit_assignment | AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment | reinforce_learning, reasoning, llm, reward_modeling, self_evolving_agents |
| 20260520_skillgenbench_benchmarking_skill_generation_llm_agents | SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents | agent_architecture, evaluation, skill_curation, llm, reasoning |
| 20260521_methodology_selecting_composing_runtime_architecture_patterns_production_llm_agents | A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents | agent_architecture, distributed_systems, multi_agent_systems, llm, reasoning |
| 20260522_calmem_dual_memory_conversational_ai | Application-Layer Dual Memory for Conversational AI: Achieving Virtually Unbounded Context Without Model Modification | memory_mechanism, long_term_memory, agent_architecture, rag, context_engineering |
| 20260523_moss_self_evolution_source_level_rewriting | MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems | self_evolving_agents, agent_architecture, llm, multi_agent_systems |
| 20260524_vector_policy_optimization_vpo | Vector Policy Optimization: Training for Diversity Improves Test-Time Search | reinforce_learning, llm, test_time_scaling, reasoning, reward_modeling |
| 20260525_gated_deltanet_2_decoupling_erase_write_linear_attention | Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention | memory_mechanism, llm, reasoning, long_term_memory, reinforce_learning |
| 20260526_skillopt_executive_strategy_self_evolving_agent_skills | SkillOpt: Executive Strategy for Self-Evolving Agent Skills | self_evolving_agents, skill_curation, agent_architecture, reasoning, workflow_optimization |
| 20260527_scaling_harness_agentic_ai | From Model Scaling to System Scaling: Scaling the Harness in Agentic AI | agent_architecture, memory_mechanism, reasoning, self_evolving_agents, multi_agent_systems |
| 20260528_CORE_contrastive_reflection_reasoning | CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning | reasoning, memory_mechanism, self_evolving_agents, contrastive_reflection, reinforce_learning, cognitive_science |
| 20260528_muse_autoskill_self_evolving_skill_memory | MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation | agent_architecture, memory_mechanism, self_evolving_agents, skill_curation, continual_learning |
| 20260528_unlocking_working_memory_latent_reasoning | Unlocking the Working Memory of Large Language Models for Latent Reasoning | memory_mechanism, reasoning, llm, reasoning_memory, context_engineering |
| 20260529_agent_lifespan_engineering_for_deployed_systems | Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems | memory_mechanism, long_term_memory, agent_architecture, evaluation, self_evolving_agents |
| 20260529_stop_comparing_llm_agents_without_disclosing_harness | Stop Comparing LLM Agents Without Disclosing the Harness | agent_architecture, evaluation, llm, multi_agent_systems, reasoning |
| 20260601_locally_coherent_globally_incoherent_multi_component_llm_agents | Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents | multi_agent_systems, reasoning, agent_architecture, evaluation |
| 20260603_agentcl_continual_learning_language_agents | AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents | continual_learning, memory_mechanism, agent_architecture, evaluation, self_evolving_agents |
| 20260604_agent_memory_characterization_system_implications | Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads | memory_mechanism, agent_architecture, long_term_memory, llm, evaluation |
| 20260604_language_models_need_sleep_self_modify_consolidate_memories | Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories | memory_mechanism, self_evolving_agents, continual_learning, reinforce_learning, reasoning, llm |
| 20260604_pretraining_recurrent_networks_without_recurrence | Pretraining Recurrent Networks without Recurrence | memory_mechanism, recurrent_neural_networks, llm, reinforce_learning, neuro_science |
| 20260605_aip_graph_representation_for_learning_and_governing_agent_skills | AIP: A Graph Representation for Learning and Governing Agent Skills | agent_architecture, skill_curation, self_evolving_agents, reasoning, workflow_optimization |
| 20260608_handoff_humanoid_agentic_whole_body_control | HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers | embodied_ai, robotics, agent_architecture, multimodal, sim_to_real |
| 20260609_socratic_swe_self_evolving_coding_agents_trace_derived_skills | Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills | self_evolving_agents, memory_mechanism, skill_curation, reinforce_learning, reasoning |
| 20260610_searchswarm_delegation_intelligence_agentic_llm_long_horizon_research | SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research | agent_architecture, multi_agent_systems, reasoning, workflow_optimization, reasoning_memory |
| 20260611_trace_unified_rollout_budget_allocation_agentic_rl | TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning | reinforce_learning, reasoning, agent_architecture, test_time_scaling, llm |
| 20260617_evolvenav_proactive_preflection_self_evolving_memory | EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation | embodied_ai, semantic_navigation, self_evolving_agents, llm, memory_mechanism |
| 20260618_fixed_point_reasoners_stable_adaptive_deep_looped_transformers | Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers | reasoning, llm, recurrent_neural_networks, memory_mechanism, agent_architecture |
| 20260622_how_transparent_is_diffusiongemma | How Transparent is DiffusionGemma? | llm, reasoning, agent_security, evaluation, interpretability |
| 20260624_evoarena_tracking_memory_evolution | EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments | memory_mechanism, agent_architecture, llm, evaluation, embodied_ai |
| 20260624_self_harness | Self-Harness: Harnesses That Improve Themselves | agent_architecture, self_evolving_agents, llm, reasoning, test_time_scaling |
| 20260624_world_models_in_pieces_structural_certification | World Models in Pieces: Structural Certification for General Agents | reinforce_learning, reasoning, agent_architecture, evaluation, foundation_agents |
| 20260626_progress_advantage_llm_agents | Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents | reinforce_learning, reward_modeling, test_time_scaling, agent_architecture, llm, reasoning |
| 20260627_joint_learning_experiential_rules_policies_llm_agents | Joint Learning of Experiential Rules and Policies for Large Language Model Agents | memory_mechanism, reinforce_learning, self_evolving_agents, reasoning, agent_architecture |
| 20260628_omniact_omnimodal_embodied_agents | Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy | embodied_ai, agent_architecture, long_term_memory, multimodal, robotics, reasoning |
| 20260629_carve_content_aware_recurrent_value_efficiency | CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention | memory_mechanism, recurrent_neural_networks, llm, reasoning, linear_attention |
| 20260629_memory_r1_enhancing_llm_agents_manage_utilize_memories_rl | Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning | agent_architecture, memory_mechanism, reinforce_learning, llm, long_term_memory |
| 20260630_from_tokens_to_states_llms_world_models | From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond | llm, reasoning, world_model, memory_mechanism, agent_architecture |
| 20260701_severa_verified_synthesis_self_evolving_agents | SEVerA: Verified Synthesis of Self-Evolving Agents | agent_architecture, self_evolving_agents, reinforce_learning, reasoning, agent_security |
| 20260702_memory_in_the_age_of_ai_agents_a_survey | Memory in the Age of AI Agents: A Survey — Forms, Functions and Dynamics | memory_mechanism, agent_architecture, survey, llm, long_term_memory |
| 20260703_self_evolving_world_models_llm_agent_planning | Self-Evolving World Models for LLM Agent Planning | world_model, self_evolving_agents, memory_mechanism, embodied_ai, reasoning |
| 20260705_llm_agents_social_structure_latent_objective_emergence | What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates | multi_agent_systems, social_simulation, agent_architecture, reasoning, llm, evaluation |
| 20260706_demopsd_disagreement_modulated_policy_self_distillation | DemoPSD: Disagreement-Modulated Policy Self-Distillation | reinforce_learning, reasoning, llm, self_evolving_agents |
| 20260707_evopolicygym_evaluating_autonomous_policy_evolution | EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments | embodied_ai, reinforce_learning, self_evolving_agents, evaluation, agent_architecture |
| 20260708_adacurl_adaptive_curriculum_rl | AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting | reinforce_learning, llm, reasoning, agent_architecture, evaluation |
| 20260708_solving_million_step_llm_zero_errors | Solving a Million-Step LLM Task with Zero Errors | multi_agent_systems, reasoning, agent_architecture, llm, test_time_scaling |
| 20260710_let_the_agent_search_tkgqa | Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering | knowledge_graph, multi_hop_reasoning, llm, agent_architecture, reasoning |
| 20260710_loger_long_context_geometric_reconstruction | LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory | long_term_memory, memory_mechanism, embodied_ai, multimodal, deep_learning |
| 20260713_metacognition_in_llms_foundations_progress_opportunities | Metacognition in LLMs: Foundations, Progress, and Opportunities | llm, reasoning, cognitive_science, memory_mechanism, agent_architecture |
| 20260713_shared_selective_persistent_memory_agentic_llm | Shared Selective Persistent Memory for Agentic LLM Systems | agent_architecture, memory_mechanism, long_term_memory, multi_agent_systems, context_engineering |
| 20260714_comprehensive_survey_knowledge_graph_reasoning_approaches_applications | A Comprehensive Survey of Knowledge Graph Reasoning: Approaches and Applications | knowledge_graph, multi_hop_reasoning, reasoning, llm, survey |
| 20260714_rubrics_as_rewards_reinforcement_learning_beyond_verifiable_domains | Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains | reinforce_learning, reward_modeling, llm, reasoning, evaluation |
| 20260716_immersion_in_github_universe_scaling_coding_agents_mastery | Immersion in the GitHub Universe: Scaling Coding Agents to Mastery | multi_agent_systems, software_engineering, coding_agents, self_evolving_agents, data_scaling |
| 20260716_prefill_as_service_kv_cache_cross_datacenter | Prefill-as-a-Service: KV Cache of Next-Generation Models Could Go Cross-Datacenter | llm_serving, kv_cache, distributed_systems, multi_agent_systems, reasoning |
| 20260717_experience_memory_graph_one_shot_error_correction_for_agents | Experience Memory Graph: One-Shot Error Correction for Agents | memory_mechanism, agent_architecture, reasoning, long_term_memory, knowledge_graph |
| 20260719_t2mlr_transformer_temporal_middle_layer_recurrence | T²MLR: Transformer with Temporal Middle-Layer Recurrence | reasoning, llm, memory_mechanism, recurrent_neural_networks, reasoning_memory |
| 20260722_supra_cognitive_modes_routed_agent_memory | Supra Cognitive Modes: A Routed Architecture for Agent Memory | agent_architecture, memory_mechanism, long_term_memory, reasoning, multi_hop_reasoning |
| 20260723_copy_less_ground_more_evidence_aware_rl | Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning | reasoning, reinforce_learning, reward_modeling, context_engineering, llm |
| 20260724_pro_long_programmatic_memory_long_horizon_reasoning | PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning | memory_mechanism, agent_architecture, reasoning, long_term_memory, coding_agents, continual_learning |
| 20260725_evolving_commitments_self_adaptive_sts | Evolving Commitments for Self-Adaptive Socio-Technical Systems | multi_agent_systems, agent_architecture, software_engineering, self_evolving_agents, reasoning |
| 20260725_monitoring_diagnosing_software_requirements | Monitoring and Diagnosing Software Requirements | software_engineering, reasoning, symbolic_reasoning, knowledge_graph, agent_architecture |
| 20260726_agentic_context_management_memory_cost_lifecycle_architecture | Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems | agent_architecture, memory_mechanism, context_engineering, reasoning, long_term_memory |
| 20260731_memrl_self_evolving_agents_runtime_rl_episodic_memory | MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory | memory_mechanism, reinforce_learning, agent_architecture, llm, reasoning, long_term_memory |