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

Observation 67b611d2-1277-424a-96f0-bd6abc117c0c · outbound

This paper cites A survey of self-evolving agents: What, when, how, and where to evolve on the path to artificial super intelligence.Transactions on Machine Learning Research, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? A survey of self-evolving agents: What, when, how, and where to evolve on the path to artificial super intelligence.Transactions on Machine Learning Research, 2026

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:30.678535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15c3b5f3-0cc4-407d-97dd-53e6f149a015 · outbound

This paper cites Position: Agentic evolution is the path to evolving llms.arXiv preprint arXiv:2602.00359, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Position: Agentic evolution is the path to evolving llms.arXiv preprint arXiv:2602.00359, 2026

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:30.740362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774e17c1-81ba-4c06-8184-c3942a218a0c · outbound

This paper cites A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:30.844983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6d0b54b-6b3b-4420-ba41-a3bb96d97d7c · outbound

This paper cites Agentic context engineering: Evolving contexts for self-improving language models.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Agentic context engineering: Evolving contexts for self-improving language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:30.945741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b30595c-b4bf-4321-82f1-c1ac004ba677 · outbound

This paper cites Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.047941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d1cbd62-4880-457e-9d8e-76e4c51ce49d · outbound

This paper cites A-mem: Agentic memory for llm agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? A-mem: Agentic memory for llm agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.168633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b4a68ac-830d-4563-8af2-bc2c42882100 · outbound

This paper cites MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.238737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9997acb5-415b-4035-aced-f5f12b482392 · outbound

This paper cites Autoskill: Experience-driven lifelong learning via skill self-evolution.arXiv preprint arXiv:2603.01145, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Autoskill: Experience-driven lifelong learning via skill self-evolution.arXiv preprint arXiv:2603.01145, 2026

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.339997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae5e5f3-dae5-48a1-9f88-e580831d52be · outbound

This paper cites Le, Samira Daruki, Xiangru Tang, Vishy Tirumalashetty, George Lee, Mahsan Rofouei, Hangfei Lin, Jiawei Han, Chen-Yu Lee, and Tomas Pfister.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Le, Samira Daruki, Xiangru Tang, Vishy Tirumalashetty, George Lee, Mahsan Rofouei, Hangfei Lin, Jiawei Han, Chen-Yu Lee, and Tomas Pfister

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.448963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669b2ad1-81a2-4075-bd74-1379c5d0b903 · outbound

This paper cites Memento-skills: Let agents design agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Memento-skills: Let agents design agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.553680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aff5ba51-e69a-4fe0-958c-0ca5c67e030e · outbound

This paper cites Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.613003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8650ca55-dd31-4e2b-b6c2-2e8233c3b8e2 · outbound

This paper cites Appworld: A controllable world of apps and people for benchmarking interactive coding agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Appworld: A controllable world of apps and people for benchmarking interactive coding agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.709243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0313bafd-50e0-4c88-95b5-24fa3f54c936 · outbound

This paper cites Gonzalez.

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

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.826496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 192ac56d-3eb2-4e4d-966f-b596268400d9 · outbound

This paper cites Swe-bench: Can language models resolve real-world github issues? In Proc.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Swe-bench: Can language models resolve real-world github issues? In Proc

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.918060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22fc5a9-a231-4699-b27a-21e74d18ae93 · outbound

This paper cites Humanity's Last Exam.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Humanity's Last Exam

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:31.996592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45ed4434-2e42-4aac-a302-79bb5630afb5 · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.087301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab7ed43-9bc6-413b-8b5e-082f746f58f4 · outbound

This paper cites Stream- bench: Towards benchmarking continuous improvement of language agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Stream- bench: Towards benchmarking continuous improvement of language agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.156197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19de0ee3-c2cd-4dac-84f9-1710b859a36c · outbound

This paper cites Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.201860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8cc89d3-74d9-495a-a8d0-64d85f8c11ec · outbound

This paper cites OpenAI GPT-5 System Card.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? OpenAI GPT-5 System Card

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.267699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba34156-2f11-4e2f-be16-4be50f196bea · outbound

This paper cites Gemini 3.1 Pro model card, February 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Gemini 3.1 Pro model card, February 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.359163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ba58dd-a90c-4480-9b54-3e6fb70502a1 · outbound

This paper cites Introducing Claude Opus 4.7, April 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Introducing Claude Opus 4.7, April 2026

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.441241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e4e000b-6c7e-4e9c-b814-b4951cdeda99 · outbound

This paper cites Browsecomp-plus: A more fair and transparent evaluation benchmark of deep-research agent.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Browsecomp-plus: A more fair and transparent evaluation benchmark of deep-research agent

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.517774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9c9edd8-577d-471a-81e4-899bf8f7293c · outbound

This paper cites Test-time training with self-supervision for generalization under distribution shifts.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Test-time training with self-supervision for generalization under distribution shifts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.557621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ef7ec98-9596-452d-b766-b5a37395abac · outbound

This paper cites Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.616665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ec2d7e4-606f-45df-bcbf-08412cdd5a1a · outbound

This paper cites Overcoming catastrophic forgetting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526, 2017.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Overcoming catastrophic forgetting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526, 2017

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.706158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7128a647-c5e2-4fc7-bee4-44afb379adaa · outbound

This paper cites Gradient episodic memory for continual learning.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Gradient episodic memory for continual learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.785239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b29ec8-639f-4f57-9e71-ec2d6c5b41ed · outbound

This paper cites Scaling llm test-time compute optimally can be more effective than scaling model parameters.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Scaling llm test-time compute optimally can be more effective than scaling model parameters

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.834609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea24b3aa-c55c-429d-8f36-4f6fd65c80e7 · outbound

This paper cites Test-time training on nearest neighbors for large language models.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Test-time training on nearest neighbors for large language models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.907311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69b76d30-5c03-4755-a817-87bedd5539bf · outbound

This paper cites Efficiently learning at test-time: Active fine-tuning of llms.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Efficiently learning at test-time: Active fine-tuning of llms

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.947220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8353d4e8-7813-4986-b32e-8b3fd29c1545 · outbound

This paper cites The surprising effectiveness of test-time training for few-shot learning.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? The surprising effectiveness of test-time training for few-shot learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:32.990733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aaae17b-f559-45b8-b4aa-042734c11429 · outbound

This paper cites In-place test-time training.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? In-place test-time training

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.052856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78bb23fd-0340-46e7-a979-5c9cb6c60f57 · outbound

This paper cites Test-time adaptation for llm agents via environment interaction.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Test-time adaptation for llm agents via environment interaction

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.147161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c6d34b6-56e8-42fd-be9c-40b104d6fb5b · outbound

This paper cites Test-time learning for large language models.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Test-time learning for large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.266388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31c98bfe-fc30-4da1-b482-26138dfd8ce1 · outbound

This paper cites Ttrl: Test-time reinforcement learning.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Ttrl: Test-time reinforcement learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.347224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560c579e-c5e5-4904-893b-432431fa2cb1 · outbound

This paper cites Learn- ing on the job: Test-time curricula for targeted reinforcement learning.arXiv preprint arXiv:2510.04786, 2025.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Learn- ing on the job: Test-time curricula for targeted reinforcement learning.arXiv preprint arXiv:2510.04786, 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.407176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 729ca982-0b5d-48a6-bc45-3aa1aa448f4f · outbound

This paper cites Learning to discover at test time.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Learning to discover at test time

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.486960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dbd5315-bd55-49ce-a095-a6213b44dc44 · outbound

This paper cites Collaborative multi-agent test-time reinforcement learning for reasoning.arXiv preprint arXiv:2601.09667, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Collaborative multi-agent test-time reinforcement learning for reasoning.arXiv preprint arXiv:2601.09667, 2026

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.584703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a992a21-8df4-4314-91b8-8d6506facb9c · outbound

This paper cites What if consensus lies? selective-complementary reinforcement learning at test time.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? What if consensus lies? selective-complementary reinforcement learning at test time

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.672842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cb42fec-7ea7-47d8-add2-4a5c603aa6c1 · outbound

This paper cites Ttsr: Test-time self-reflection for continual reasoning improvement.arXiv preprint arXiv:2603.03297, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Ttsr: Test-time self-reflection for continual reasoning improvement.arXiv preprint arXiv:2603.03297, 2026

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.783687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d76d5b23-7867-48c6-ba76-c7b3adbf5fd3 · outbound

This paper cites Ttcs: Test-time curriculum synthesis for self-evolving.arXiv preprint arXiv:2601.22628, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Ttcs: Test-time curriculum synthesis for self-evolving.arXiv preprint arXiv:2601.22628, 2026

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:33.899505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b01a108e-71ff-4206-a9bc-190f1a4e571e · outbound

This paper cites Test-Time Learning with an Evolving Library.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Test-Time Learning with an Evolving Library

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.009288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb9d85b7-402a-49fc-aec2-7efb0b250981 · outbound

This paper cites Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.114246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2262f2-6162-4fac-abde-a3da7f3f3208 · outbound

This paper cites Tarse: Test-time adaptation via retrieval of skills and experience for reasoning agents.arXiv preprint arXiv:2603.01241, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Tarse: Test-time adaptation via retrieval of skills and experience for reasoning agents.arXiv preprint arXiv:2603.01241, 2026

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.226463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26fb1c9a-50dd-4827-84ac-1aa5afaa48dd · outbound

This paper cites Agentic plan caching: Test-time memory for fast and cost-efficient llm agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Agentic plan caching: Test-time memory for fast and cost-efficient llm agents

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.337320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed2c9bfc-f745-4cf6-b322-a65549161db3 · outbound

This paper cites TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.442077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18107843-204b-4eb5-b983-e6c2028238e2 · outbound

This paper cites Self-improving llm agents at test-time.arXiv preprint arXiv:2510.07841, 2025.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Self-improving llm agents at test-time.arXiv preprint arXiv:2510.07841, 2025

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.540281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b09b02a8-d8b8-453a-b705-88ffabf8a7c3 · outbound

This paper cites Just- in-time reinforcement learning: Continual learning in llm agents without gradient updates.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Just- in-time reinforcement learning: Continual learning in llm agents without gradient updates

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.652568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f5ea4cc-4e98-4228-9cbd-eb3796899c71 · outbound

This paper cites Panini: Continual learning in token space via structured memory.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Panini: Continual learning in token space via structured memory

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.761418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a6a2359-872e-42b0-bcc8-368eb0a6533b · outbound

This paper cites Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.866944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df12cecf-038a-4dc1-8a2b-c5be36a6d665 · outbound

This paper cites Mssr: Memory-aware adaptive replay for continual llm fine-tuning.arXiv preprint arXiv:2603.09892, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Mssr: Memory-aware adaptive replay for continual llm fine-tuning.arXiv preprint arXiv:2603.09892, 2026

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:34.939316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec8e04f-7212-49fe-a4ed-8b154e68aa71 · outbound

This paper cites Learning to continually learn via meta-learning agentic memory designs.arXiv preprint arXiv:2602.07755, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Learning to continually learn via meta-learning agentic memory designs.arXiv preprint arXiv:2602.07755, 2026

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.017911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb473b65-f10e-480b-bb9b-04a615958777 · outbound

This paper cites Xskill: Continual learning from experience and skills in multimodal agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Xskill: Continual learning from experience and skills in multimodal agents

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.087726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da43f976-c6ce-463c-9799-361ce994f6aa · outbound

This paper cites Online Experiential Learning for Language Models.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Online Experiential Learning for Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.159727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc78d07-c649-491c-9b06-7196fe1fb0e7 · outbound

This paper cites Adaptive collaboration with humans: Metacognitive policy optimization for multi-agent llms with continual learning.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Adaptive collaboration with humans: Metacognitive policy optimization for multi-agent llms with continual learning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.227678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d42845b4-b90e-46aa-b1b5-2dbf86837931 · outbound

This paper cites MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.336093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 227b17f5-290a-48c0-94bd-9da4a8674c98 · outbound

This paper cites Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.459460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6271b35-7585-4cff-ac8d-17152f2132e8 · outbound

This paper cites SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.579166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fcce961-c4c5-4a04-8cba-613fc43b0b43 · outbound

This paper cites SkillOS: Learning Skill Curation for Self-Evolving Agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? SkillOS: Learning Skill Curation for Self-Evolving Agents

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.690973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d83db8-2aa5-4635-b235-d2f7d73e311e · outbound

This paper cites EvoSkill: Automated Skill Discovery for Multi-Agent Systems.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? EvoSkill: Automated Skill Discovery for Multi-Agent Systems

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.780877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a4cd23-7cf0-42d9-bfbc-c364071b1d2d · outbound

This paper cites OpenSkill: Open-World Self-Evolution for LLM Agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? OpenSkill: Open-World Self-Evolution for LLM Agents

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:35.900154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3406787a-4e71-4b33-9ab7-b8a54d9deec6 · outbound

This paper cites SkillOpt: Executive Strategy for Self-Evolving Agent Skills.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.013114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f8206b5-8e87-4d2a-82ea-3561f5a75200 · outbound

This paper cites Meta-Harness: End-to-End Optimization of Model Harnesses.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Meta-Harness: End-to-End Optimization of Model Harnesses

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.133344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4deb2ae-ff8d-44e6-a47e-4bf4271f2963 · outbound

This paper cites Evoconfig: Self-evolving multi-agent systems for efficient autonomous environment configuration.arXiv preprint arXiv:2601.16489, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Evoconfig: Self-evolving multi-agent systems for efficient autonomous environment configuration.arXiv preprint arXiv:2601.16489, 2026

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.247731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd65faba-7aaf-4848-ae01-57b277ee676c · outbound

This paper cites Selaur: Self evolving llm agent via uncertainty-aware rewards.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Selaur: Self evolving llm agent via uncertainty-aware rewards

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.328391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78298233-2985-415e-a37a-9f4e5254b1ca · outbound

This paper cites Self-Improving Language Models with Bidirectional Evolutionary Search.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Self-Improving Language Models with Bidirectional Evolutionary Search

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.464200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42b75e4e-19e0-460c-86e8-ec6acc6fd764 · outbound

This paper cites Tool-r0: Self-evolving llm agents for tool-learning from zero data.arXiv preprint arXiv:2602.21320, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Tool-r0: Self-evolving llm agents for tool-learning from zero data.arXiv preprint arXiv:2602.21320, 2026

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.602393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2e9eb84-99d0-47dc-beda-b6654d619d6a · outbound

This paper cites Rein- forcing chain-of-thought reasoning with self-evolving rubrics.arXiv preprint arXiv:2602.10885, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Rein- forcing chain-of-thought reasoning with self-evolving rubrics.arXiv preprint arXiv:2602.10885, 2026

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.737392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d4c3a23-e484-4c81-82a6-2206d90e5e79 · outbound

This paper cites Metagen: Self-evolving roles and topologies for multi-agent llm reasoning.arXiv preprint arXiv:2601.19290, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Metagen: Self-evolving roles and topologies for multi-agent llm reasoning.arXiv preprint arXiv:2601.19290, 2026

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:36.901016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81c2eb88-de5c-4ea8-b3e8-4ef04ac48b49 · outbound

This paper cites Self-evolving multi-agent collaboration networks for software development.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Self-evolving multi-agent collaboration networks for software development

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.006298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb119d41-1db2-491c-b863-2c7cd2db0aad · outbound

This paper cites SEW: Self-Evolving Agentic Workflows for Automated Code Generation.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? SEW: Self-Evolving Agentic Workflows for Automated Code Generation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.085301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a438e6fe-bc99-4020-aadc-cd4a1d5f5693 · outbound

This paper cites Evotool: Self-evolving tool-use policy optimization in llm agents via blame-aware mutation and diversity-aware selection.arXiv preprint arXiv:2603.04900, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Evotool: Self-evolving tool-use policy optimization in llm agents via blame-aware mutation and diversity-aware selection.arXiv preprint arXiv:2603.04900, 2026

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.179134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ecd6a5f-8ebc-4011-8b8c-1248324a388d · outbound

This paper cites AlphaEvolve: A coding agent for scientific and algorithmic discovery.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? AlphaEvolve: A coding agent for scientific and algorithmic discovery

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.248349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a19d7cd-4a82-425a-8a93-a521749a1200 · outbound

This paper cites Evotest: Evolutionary test-time learning for self-improving agentic systems.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Evotest: Evolutionary test-time learning for self-improving agentic systems

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.318781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a3b0b20-44fa-43b8-a733-cfb5ed07a0be · outbound

This paper cites Building self-evolving agents via experience-driven lifelong learning: A framework and benchmark.arXiv preprint arXiv:2508.19005, 2026.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Building self-evolving agents via experience-driven lifelong learning: A framework and benchmark.arXiv preprint arXiv:2508.19005, 2026

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.425048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b76f30c6-aa60-4f0a-8914-2712ff2475be · outbound

This paper cites Optimizing generative ai by backpropagating language model feedback.Nature, 639:609–616, 2025.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Optimizing generative ai by backpropagating language model feedback.Nature, 639:609–616, 2025

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.498006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73fce81a-b1bf-4152-9555-ee4a82465c9c · outbound

This paper cites Your agent may misevolve: Emergent risks in self-evolving llm agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Your agent may misevolve: Emergent risks in self-evolving llm agents

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.591245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6b8e116-6b94-4a8e-8c9e-eafca8f43605 · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Webshop: Towards scalable real-world web interaction with grounded language agents

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.698493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2935ea0f-764a-4a2a-8341-5d42cd473aad · outbound

This paper cites Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.811240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 188f85ae-edff-4a3f-aa09-91fc9df16cc3 · outbound

This paper cites Webvoyager: Building an end-to-end web agent with large multimodal models.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Webvoyager: Building an end-to-end web agent with large multimodal models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.916387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf78fd0c-0c32-48c7-86ad-fc0033c497ef · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:37.996496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592bab4f-14f5-43de-8234-c160ebd7d284 · outbound

This paper cites MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.075464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f05cad0a-6ce5-48e5-82e9-5d21a17a8a02 · outbound

This paper cites The tool decathlon: Benchmarking language agents for diverse, realistic, and long-horizon task execution.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? The tool decathlon: Benchmarking language agents for diverse, realistic, and long-horizon task execution

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.158997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02c2e747-2463-4d6e-b47b-e9c0e5f07032 · outbound

This paper cites Terminal-bench: Benchmarking agents on hard, realistic tasks in command line interfaces.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Terminal-bench: Benchmarking agents on hard, realistic tasks in command line interfaces

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.214251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cc7197c-1adf-4548-8a30-f846e95381f2 · outbound

This paper cites Cybergym: Evaluating AI agents’ real-world cybersecurity capabilities at scale.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Cybergym: Evaluating AI agents’ real-world cybersecurity capabilities at scale

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.287770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81771bf5-edef-4fed-94ad-808de9210a98 · outbound

This paper cites SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.372036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6e25965-c2c8-4b22-b36c-349ab6a533c4 · outbound

This paper cites SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.455621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47a9d7b-74e2-4fe3-8fbd-963edfbf6074 · outbound

This paper cites Gaia: a benchmark for general ai assistants.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Gaia: a benchmark for general ai assistants

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.536812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b512849c-9191-4ddc-a38b-e8badd0f1281 · outbound

This paper cites BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.625544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0dc2de-6651-456f-a1aa-1c902b2c9a9f · outbound

This paper cites GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.705418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f015896-0a35-463c-a30a-23394db146bc · outbound

This paper cites Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.779498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba0c0772-e8a4-4962-8322-b8fd75fcc637 · outbound

This paper cites Agent workflow memory.

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

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:38.857487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62aa1b8c-60ad-45aa-9b9b-2d5cc21f14e3 · outbound

This paper cites none identified.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? none identified

Reference 92

Resolution: malformed identifier; no resolver link, observed 2026-08-04T01:12:38.939920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3377049d-f4bc-4c76-8fb7-557fa03b9c9e · outbound

This paper cites reasoning.

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

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.018297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2a5d1a1-0e80-419f-9eef-e66ae93408dc · outbound

This paper cites Order from most to least important.

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Order from most to least important

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.092541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f10004a5-26a9-4d39-95d1-277af5e60038 · outbound

This paper cites an unresolved cited work.

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

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.153063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90dc9e6e-7d6c-4c87-8624-ff0085958f7c · outbound

This paper cites Status:.

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

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.230523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53aba8b1-c42c-45e0-9c21-a9a2afb989b4 · outbound

This paper cites an unresolved cited work.

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

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.310212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09cd7c8b-48af-4bba-ade3-477b10cbe395 · outbound

This paper cites an unresolved cited work.

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

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.419533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00a09f38-aa8c-413d-a4b4-396c781e0e26 · outbound

This paper cites an unresolved cited work.

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

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.476352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6984840c-21ed-47f3-a1db-0713b084276d · outbound

This paper cites an unresolved cited work.

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

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-04T01:12:39.559055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers