MemEvolve jointly evolves agent experiential knowledge and memory architectures via a modular codebase, delivering up to 17% gains on agent benchmarks with cross-task and cross-model generalization.
hub
Alita: Generalist agent enabling scalable agentic reasoning with minimal predefinition and maximal self-evolution
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
abstract
Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually predefined tools and workflows, which hinder their adaptability, scalability, and generalization across domains. In this work, we introduce Alita--a generalist agent designed with the principle of "Simplicity is the ultimate sophistication," enabling scalable agentic reasoning through minimal predefinition and maximal self-evolution. For minimal predefinition, Alita is equipped with only one component for direct problem-solving, making it much simpler and neater than previous approaches that relied heavily on hand-crafted, elaborate tools and workflows. This clean design enhances its potential to generalize to challenging questions, without being limited by tools. For Maximal self-evolution, we enable the creativity of Alita by providing a suite of general-purpose components to autonomously construct, refine, and reuse external capabilities by generating task-related model context protocols (MCPs) from open source, which contributes to scalable agentic reasoning. Notably, Alita achieves 75.15% pass@1 and 87.27% pass@3 accuracy, which is top-ranking among general-purpose agents, on the GAIA benchmark validation dataset, 74.00% and 52.00% pass@1, respectively, on Mathvista and PathVQA, outperforming many agent systems with far greater complexity. More details will be updated at $\href{https://github.com/CharlesQ9/Alita}{https://github.com/CharlesQ9/Alita}$.
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Metis combines text and code memory hierarchically for self-evolving agents, claiming up to 20.6% higher accuracy and 22.8% lower cost than ReAct on the AppWorld benchmark.
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compete with much larger ones.
MetaForge proposes a self-evolving multimodal agent with decide-retrieve-adapt-forge-recycle stages jointly optimized by RL to dynamically manage and create tools, outperforming baselines on 12 benchmarks.
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
BoundaryRouter routes queries to LLM or agent using early experience memory from a seed set, cutting inference time 60.6% versus always using agents and raising performance 28.6% versus always using direct LLM inference.
DRIVE disentangles reasoning and interaction skills for web agents via dual-level modeling and scene-aware coordination, reaching 52.8% success on WebArena tasks.
MGA is a memory-driven GUI agent that uses an observer for bias-free screen reading and structured memory for compact state transitions to enable efficient long-horizon automation.
EvoSOP enables LLM agents to self-evolve by iteratively synthesizing atomic tool actions into reusable Standard Operating Procedures, improving success rates and reducing reasoning rounds on ACEBench and Tau2Bench.
Self-evolving LLM agents introduce persistent, amplifying security threats that static defenses cannot address, as shown by analysis of 25 attack surface cells and case studies.
Agent libOS is a runtime substrate for capability-controlled self-evolving LLM agents that completed 27 deterministic tasks without unauthorized side effects while maintaining a 7% false-denial rate.
AGP decouples agent resources from a closed-loop self-evolution interface; AGS using it reports consistent gains on long-horizon multi-resource agent benchmarks.
SimpleMem proposes semantic structured compression, online synthesis, and intent-aware retrieval to create efficient lifelong memory for LLM agents, reporting 26.4% F1 gains and up to 30x lower token use on LoCoMo benchmarks.
UI-TARS-2 reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld while attaining 59.8 mean normalized score on a 15-game suite through multi-turn RL and scalable data generation.
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
Selecting preference pairs whose DPO implicit reward gap is small yields better LLM alignment than random or baseline selection while using only 10% of the data.
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
citing papers explorer
-
MemEvolve: Meta-Evolution of Agent Memory Systems
MemEvolve jointly evolves agent experiential knowledge and memory architectures via a modular codebase, delivering up to 17% gains on agent benchmarks with cross-task and cross-model generalization.
-
Metis: Bridging Text and Code Memory for Self-Evolving Agents
Metis combines text and code memory hierarchically for self-evolving agents, claiming up to 20.6% higher accuracy and 22.8% lower cost than ReAct on the AppWorld benchmark.
-
MetaPS: Adaptive Programmatic Strategy Selection for Market Agents
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
-
OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation
OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compete with much larger ones.
-
MetaForge: A Self-Evolving Multimodal Agent that Retrieves, Adapts, and Forges Tools On Demand
MetaForge proposes a self-evolving multimodal agent with decide-retrieve-adapt-forge-recycle stages jointly optimized by RL to dynamically manage and create tools, outperforming baselines on 12 benchmarks.
-
Rethinking Memory as Continuously Evolving Connectivity
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
-
Learning Agent Routing From Early Experience
BoundaryRouter routes queries to LLM or agent using early experience memory from a seed set, cutting inference time 60.6% versus always using agents and raising performance 28.6% versus always using direct LLM inference.
-
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
DRIVE disentangles reasoning and interaction skills for web agents via dual-level modeling and scene-aware coordination, reaching 52.8% success on WebArena tasks.
-
MGA: Memory-Driven GUI Agent for Observation-Centric Interaction
MGA is a memory-driven GUI agent that uses an observer for bias-free screen reading and structured memory for compact state transitions to enable efficient long-horizon automation.
-
From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
EvoSOP enables LLM agents to self-evolve by iteratively synthesizing atomic tool actions into reusable Standard Operating Procedures, improving success rates and reducing reasoning rounds on ACEBench and Tau2Bench.
-
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Self-evolving LLM agents introduce persistent, amplifying security threats that static defenses cannot address, as shown by analysis of 25 attack surface cells and case studies.
-
Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents
Agent libOS is a runtime substrate for capability-controlled self-evolving LLM agents that completed 27 deterministic tasks without unauthorized side effects while maintaining a 7% false-denial rate.
-
Autogenesis: A Self-Evolving Agent Protocol
AGP decouples agent resources from a closed-loop self-evolution interface; AGS using it reports consistent gains on long-horizon multi-resource agent benchmarks.
-
SimpleMem: Efficient Lifelong Memory for LLM Agents
SimpleMem proposes semantic structured compression, online synthesis, and intent-aware retrieval to create efficient lifelong memory for LLM agents, reporting 26.4% F1 gains and up to 30x lower token use on LoCoMo benchmarks.
-
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
UI-TARS-2 reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld while attaining 59.8 mean normalized score on a 15-game suite through multi-turn RL and scalable data generation.
-
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
-
Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap
Selecting preference pairs whose DPO implicit reward gap is small yields better LLM alignment than random or baseline selection while using only 10% of the data.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
-
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
- Self-Harness: Harnesses That Improve Themselves