AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

Hugging Face Daily Papers Papers
llm-agents self-evolving streaming-tasks evaluation benchmark arxiv

Summary

AgentStream introduces a unified framework to evaluate self-evolving LLM agents under streaming task scenarios, showing that self-evolution reliability varies across scenarios and is gated by model capability.

Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the Isolated, Sequential, and Interleaved streaming scenarios at test time, which progressively vary the scope and domain composition of the stream. Over these scenarios, we combinatorially evaluate five representative self-evolving methods across three frontier foundation models, disentangling how model capability, method architecture, and streaming scenario jointly shape self-evolution. Our results show that self-evolution reliability varies across streaming scenarios, the benefit of self-evolution is gated by model capability and non-monotonic in model strength, and no single method dominates across models and scenarios. These findings offer concrete guidance for selecting self-evolving methods across models and streaming scenarios. Overall, we advocate that self-evolving agents should be evaluated under realistic task streams rather than isolated single-task settings.
Original Article
View Cached Full Text

Cached at: 08/05/26, 01:42 AM

Paper page - AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

Source: https://huggingface.co/papers/2608.00155

Abstract

Largelanguagemodel(LLM)agentscanself-evolvebycontinuallyimprovingfromtheirownaccumulatedexperience.However,existingstudiespredominantlyadoptindependentevaluation.Consequently,thebehaviorofself-evolvingagentsinrealisticstreamingsettings,whereagentsadapttodiverseandcomplextaskstreams,remainspoorlyunderstood.Toaddressthisgap,weintroduceAgentStream,aunifiedframeworkthatevaluatesself-evolvingagentsspanningdiverseevolutioncomponentsbyorganizingagenticbenchmarksintoaconfigurabletaskstreamandinstantiatingtheIsolated,Sequential,andInterleavedstreamingscenariosattesttime,whichprogressivelyvarythescopeanddomaincompositionofthestream.Overthesescenarios,wecombinatoriallyevaluatefiverepresentativeself-evolvingmethodsacrossthreefrontierfoundationmodels,disentanglinghowmodelcapability,methodarchitecture,andstreamingscenariojointlyshapeself-evolution.Ourresultsshowthatself-evolutionreliabilityvariesacrossstreamingscenarios,thebenefitofself-evolutionisgatedbymodelcapabilityandnon-monotonicinmodelstrength,andnosinglemethoddominatesacrossmodelsandscenarios.Thesefindingsofferconcreteguidanceforselectingself-evolvingmethodsacrossmodelsandstreamingscenarios.Overall,weadvocatethatself-evolvingagentsshouldbeevaluatedunderrealistictaskstreamsratherthanisolatedsingle-tasksettings.

View arXiv pageView PDFGitHub4Add to collection

Get this paper in your agent:

hf papers read 2608\.00155

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.00155 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.00155 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.00155 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution

arXiv cs.CL

CoEvolve proposes an agent-data mutual evolution framework for training LLM agents through closed-loop, interaction-driven learning that adapts both the agent and its training data distribution. The method extracts feedback signals from rollout trajectories to guide LLM-based task synthesis, demonstrating significant improvements (15-19% absolute gains) across multiple Qwen models on AppWorld and BFCL benchmarks.

OpenSkill: Open-World Self-Evolution for LLM Agents

Hugging Face Daily Papers

OpenSkill is a framework for LLM agents to self-evolve skills and verification signals from open-world resources without target-task supervision, achieving high performance across benchmarks.

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Hugging Face Daily Papers

Introduces ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning in LLM agents, showing that while sequential execution improves performance, current methods struggle to consolidate experience into robust, transferable skills.