tsinghua_university

Tsinghua University, a leading research university in China

Name	Categories	Topics	References	Credibility	Title	RelatedNotes	NavigationOrder	Eleventy	TemplateEngineOverride
20260419_memskill_learning_evolving_memory_skills	paper_analysis	self_evolving_agents, memory_mechanism, agent_architecture, llm, long_term_memory	nanyang_technological_university, tsinghua_university, university_of_illinois_urbana_champaign	100	MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents	GEMS: Agent-Native Multimodal Generation with Memory and Skills	[object Object]	[object Object]	md
20260504_self_evolving_agents_survey_asi	paper_analysis	self_evolving_agents, artificial_super_intelligence, survey, agent_architecture, memory_mechanism	princeton_university, tsinghua_university, sjtu, google_cloud_ai_research	100	A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence	ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory	[object Object]	[object Object]	md
20260507_scaling_large_language_model_multi_agent_collaboration	paper_analysis	llm, agent_architecture, workflow_optimization, distributed_systems	tsinghua_university, peng_cheng_laboratory	100	Scaling Large Language Model-based Multi-Agent Collaboration		[object Object]	[object Object]	md
20260515_harnessing_agentic_evolution	paper_analysis	agent_architecture, self_evolving_agents, reasoning, memory_mechanism, reinforce_learning, workflow_optimization	deepwisdom, hkust_gz, sjtu, tsinghua_university, nanyang_technological_university	100	harnessing_agentic_evolution	self_evolving_agents_survey_asi, skillos_learning_skill_curation_self_evolving_agents, aflow_automating_agentic_workflow_generation	[object Object]	[object Object]	md
20260520_skillgenbench_benchmarking_skill_generation_llm_agents	paper_analysis	agent_architecture, evaluation, skill_curation, llm, reasoning	quanta_alpha, sjtu, pku, nus, xjtu, tsinghua_university, sufe, ntu, ucas	100	SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents	ontology_skill_analysis	[object Object]	[object Object]	md
20260610_searchswarm_delegation_intelligence_agentic_llm_long_horizon_research	paper_analysis	agent_architecture, multi_agent_systems, reasoning, workflow_optimization, reasoning_memory	tsinghua_university, pku, ant_group, browsecomp, searchswarm	100	SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research	lintree_explicitly_structured_search_histories, aip_graph_representation_for_learning_and_governing_agent_skills, aflow_automating_agentic_workflow_generation, apwa_parallelizable_agentic_workflows, scaling_large_language_model_multi_agent_collaboration	[object Object]	[object Object]	md
20260611_trace_unified_rollout_budget_allocation_agentic_rl	paper_analysis	reinforce_learning, reasoning, agent_architecture, test_time_scaling, llm	tsinghua_university, hotpotqa, bfcl_v3, monte_carlo_tree_search	100	TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning	rl_long_horizon_reasoning_llm_expressiveness, agent_memory_and_reasoning_frontier_survey_2026	[object Object]	[object Object]	md
20260707_evopolicygym_evaluating_autonomous_policy_evolution	paper_analysis	embodied_ai, reinforce_learning, self_evolving_agents, evaluation, agent_architecture	cuhk_shenzhen, sjtu, tsinghua_university, ustc	100	EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments	demopsd_disagreement_modulated_policy_self_distillation, llm_agents_social_structure_latent_objective_emergence, recontext_recursive_evidence_replay, evolvenav_proactive_preflection_self_evolving_memory	[object Object]	[object Object]	md
20260716_prefill_as_service_kv_cache_cross_datacenter	paper_analysis	llm_serving, kv_cache, distributed_systems, multi_agent_systems, reasoning	moonshot_ai, tsinghua_university	100	Prefill-as-a-Service: KV Cache of Next-Generation Models Could Go Cross-Datacenter	20260714_comprehensive_survey_knowledge_graph_reasoning_approaches_applications, 20260714_rubrics_as_rewards_reinforcement_learning_beyond_verifiable_domains	[object Object]	[object Object]	md