Paper Citation Record · LEDGER

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

As of 5 August 2026, this Paper Citation Record lists 2 of 2 outbound references and 68 inbound Pith citation observations for arXiv:2511.20857.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2511.20857 v2

Coverage vector

measured 2 of 2 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T18:04:48.156727Z

measured 70 of 70 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 68 of 68 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T21:37:35.836340Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-04T17:20:00.018935Z

Reference resolution

2 of 2 outbound references displayed

verified exact1
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7e2fa6bd-8d0d-4e51-b189-993c0edfe3f7 · outbound

This paper cites Evaluating Very Long-Term Conversational Memory of LLM Agents.

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory Evaluating Very Long-Term Conversational Memory of LLM Agents

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-21T18:05:27.147044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 799b9935-80e0-4020-b1a5-f045028d9abb · outbound

This paper cites 1,3” or “2-4.

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory 1,3” or “2-4

Reference 2

Resolution: malformed identifier; raw_fallback, observed 2026-05-21T18:05:27.248013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 0837b2ba-1b6a-4925-a54d-0c4e790718f1 · inbound

Agentic Reasoning for Large Language Models cites this paper.

Agentic Reasoning for Large Language Models Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-17T15:14:25.765131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2d6e198c-3d5b-43e2-a5b9-11ac55bdbb70 · inbound

Toward Efficient Agents: Memory, Tool learning, and Planning cites this paper.

Toward Efficient Agents: Memory, Tool learning, and Planning Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 145

Resolution: unresolved; no resolver link, observed 2026-08-03T09:21:45.040455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2db6c0e-0fc4-41a3-9046-10b6cbba76dd · inbound

Improve Large Language Model Systems with User Logs cites this paper.

Improve Large Language Model Systems with User Logs Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-21T14:34:12.932663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 162a938e-68b1-45ea-a0c3-e5c58b3c8886 · inbound

Improve Large Language Model Systems with User Logs cites this paper.

Improve Large Language Model Systems with User Logs Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T04:00:20.314092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34861772-4e01-4d15-8107-7d542ab0be67 · inbound

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems cites this paper.

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 85f52853-f057-4f59-937f-27754691a28a · inbound

ActionNex: A Virtual Outage Manager for Cloud Computing cites this paper.

ActionNex: A Virtual Outage Manager for Cloud Computing Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 901c90a3-fe5f-49fd-9bba-0da567080a59 · inbound

TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation cites this paper.

TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0f50ded2-146e-48dd-9d83-fdbbdfd0e440 · inbound

MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought cites this paper.

MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a22e10f1-281c-4305-b4ef-f8f02df92a0e · inbound

MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought cites this paper.

MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 38

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T09:34:57.214613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a8af0925-a521-4c93-9d65-d64adcad0345 · inbound

M$^\star$: Every Task Deserves Its Own Memory Harness cites this paper.

M$^\star$: Every Task Deserves Its Own Memory Harness Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bccacb77-9bac-48a5-8127-bc4143e7a00d · inbound

Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve cites this paper.

Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4e900222-1b84-4215-827a-f08631de3ea6 · inbound

From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution cites this paper.

From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e60cb321-02d7-44c4-8bfd-a5351ade78fb · inbound

From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution cites this paper.

From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T19:51:48.531280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 542a4428-6f28-43e9-9a91-f6504d871da7 · inbound

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

SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 96ade66f-415d-475f-a0ca-790d84caf1c1 · inbound

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations cites this paper.

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d54c7b03-1909-474a-be23-6c38d24dff77 · inbound

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations cites this paper.

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1abc07e5-e386-4813-b3bf-1c4346d8eb2e · inbound

Agentic-imodels: Evolving agentic interpretability tools via autoresearch cites this paper.

Agentic-imodels: Evolving agentic interpretability tools via autoresearch Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6b35f8de-26d3-4610-85c0-9623e6a8232d · inbound

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning cites this paper.

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e9173142-86b6-423b-b790-2cd94e31e416 · inbound

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning cites this paper.

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 27e3c272-0d5b-46f2-a228-c86c589adea4 · inbound

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning cites this paper.

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 046f4948-05dc-4eeb-b9cf-00d648ced2ba · inbound

From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work cites this paper.

From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec3adc7a-e507-48a1-9c81-c7c9d35a3d10 · inbound

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications cites this paper.

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 146

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 35c27b98-50d0-43c0-825f-d6c8348da9bc · inbound

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications cites this paper.

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 148

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:19:14.814754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e87966a1-9cdc-4f5e-8d91-a6102df020e7 · inbound

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications cites this paper.

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 140

Resolution: verified exact; local_arxiv, observed 2026-06-30T23:25:07.289996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 22175fa4-fb63-4439-a326-c859a44c11fd · inbound

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents cites this paper.

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d3c3b01d-8889-4961-abcf-0aaf5839706f · inbound

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents cites this paper.

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-15T05:59:48.997096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 545925b9-4c11-4566-a109-7185f2096439 · inbound

AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization cites this paper.

AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation aaccb7a4-5374-4895-88b7-e2c25f86751a · inbound

AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization cites this paper.

AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 42

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T23:35:07.629183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f5c80c84-4e9d-4b40-ab64-e0496befc17b · inbound

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation cites this paper.

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad4452eb-2f58-4c98-97ac-ad8c2ad2c128 · inbound

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs cites this paper.

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b18eb268-a1be-4705-9d75-605a53e8741f · inbound

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading cites this paper.

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ac261d9c-b950-4c1c-8f05-92fc46e95974 · inbound

Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces cites this paper.

Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 298d372a-b8a5-44c8-be60-66a7d322fcb7 · inbound

Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces cites this paper.

Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 42

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T22:25:06.845608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7731b378-3142-4b4c-bce8-e214c85c5e38 · inbound

Context Training with Active Information Seeking cites this paper.

Context Training with Active Information Seeking Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cf3aad9b-f80b-4de0-a85f-91308d2ec64d · inbound

Context Training with Active Information Seeking cites this paper.

Context Training with Active Information Seeking Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 60

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:09:49.991157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6af1ea49-8558-49c3-a9c3-a49393cbfb23 · inbound

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation cites this paper.

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:13:16.650386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c19c32c9-dcc7-44d4-80e2-40fa9ea126dd · inbound

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents cites this paper.

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-15T04:49:44.079669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8ec255aa-ff9b-492d-a17e-5345aad3104f · inbound

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

Test-Time Learning with an Evolving Library Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-15T01:48:28.969956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c86321c1-05b6-446c-b9e4-48b35335e3cb · inbound

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

Test-Time Learning with an Evolving Library Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T14:06:40.867144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1312ebbd-7bd8-470b-86a2-ce2c58c2b570 · inbound

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory cites this paper.

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-19T16:47:40.489988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 80b0efc5-e7bb-45d7-91c6-bebcd39af8ac · inbound

EXG: Self-Evolving Agents with Experience Graphs cites this paper.

EXG: Self-Evolving Agents with Experience Graphs Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T22:17:49.338215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 88f441a7-c589-4cc2-b067-fa1df2bb3a91 · inbound

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective cites this paper.

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T11:38:14.541752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5e0676b8-bc48-4c42-b361-08a1b64eb9a0 · inbound

Code as Agent Harness cites this paper.

Code as Agent Harness Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 202

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:58:14.364346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b1eae535-c00f-4620-aeb5-00429443b89c · inbound

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents cites this paper.

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T05:39:40.764887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0c82230f-c0e9-49ba-b087-1b26e3407495 · inbound

Rethinking Memory as Continuously Evolving Connectivity cites this paper.

Rethinking Memory as Continuously Evolving Connectivity Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 53

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T12:33:24.800094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 56be5de9-6e7a-4d25-95ff-a44afd8099a3 · inbound

Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue cites this paper.

Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 60

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:42:25.950848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f6b69651-616d-4605-aebd-d29360283f78 · inbound

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents cites this paper.

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T22:56:20.164476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 18914754-6459-4567-b3c1-236c4e069731 · inbound

M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks cites this paper.

M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-07-02T08:16:47.771817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b134c7f7-175b-41f6-b55b-2fe0f6311855 · inbound

EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts cites this paper.

EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T09:06:49.133300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bf09f45e-3139-427f-b4b9-31967b364d20 · inbound

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads cites this paper.

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-02T13:36:59.295338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1343f239-25ba-481f-b88f-1e4a8892f3c6 · inbound

Tree-of-Experience: A Structured Experience-Management Solution for Self-Evolving Agents under Low-Repetition and Implicit-Reward Environments cites this paper.

Tree-of-Experience: A Structured Experience-Management Solution for Self-Evolving Agents under Low-Repetition and Implicit-Reward Environments Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:47:09.749147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 326fa9a8-b64e-4147-a12e-8da722189dbb · inbound

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory cites this paper.

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-07-03T01:07:30.920151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fcd865db-df08-447b-9b56-eaabc62d6fce · inbound

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution cites this paper.

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T03:39:30.783334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4c24f545-ca42-47ca-8bd6-d0803abc7a13 · inbound

AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents cites this paper.

AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T17:03:41.262391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d0de9262-ab7b-4fbf-ac70-6d8f9738b9e0 · inbound

MetaPS: Adaptive Programmatic Strategy Selection for Market Agents cites this paper.

MetaPS: Adaptive Programmatic Strategy Selection for Market Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 132

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T08:39:42.650845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3847d528-82cd-482e-9e54-6b382803f934 · inbound

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning cites this paper.

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 39

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T17:20:00.020604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8ec8cff0-f92f-459e-8025-d5ac0a39c4b2 · inbound

The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory cites this paper.

The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T09:55:41.341437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e4564c04-6bfd-40cc-8caf-5df5fbee1fad · inbound

What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States cites this paper.

What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 64

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T10:35:41.276404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 657e666d-7df1-4c95-a97b-fc8a2eced198 · inbound

What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States cites this paper.

What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 64

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T22:08:58.667321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 252f20b3-6da8-46dd-b279-166d986c5e88 · inbound

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments cites this paper.

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-11T07:57:43.000834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f80d9411-59af-440a-8a82-80771dacb623 · inbound

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory cites this paper.

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-14T12:26:27.446079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fb71451-e324-4a06-aa00-80c198d4a3ea · inbound

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory cites this paper.

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-02T07:21:33.187454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a12b528-c9c4-43c6-8ab8-0e1627436779 · inbound

Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents cites this paper.

Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-14T11:04:44.592375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 483f00e8-5f31-4023-a97f-b7c8743336dc · inbound

Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents cites this paper.

Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T22:44:00.259964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67342421-022f-45fd-859c-8120df1aba13 · inbound

Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting cites this paper.

Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T11:46:02.563189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e28cc05-454d-47e8-acc0-62ed074bc7e3 · inbound

RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal Reasoning cites this paper.

RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal Reasoning Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-31T16:09:14.331637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? cites this paper.

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 b3809490-a219-4107-ae23-10d6df1a983b · inbound

Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents cites this paper.

Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T21:37:35.836340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.