DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA | Paper Citation Record

Observation b6ec7e82-2512-41f7-874d-640bc0e5b5d1 · outbound

This paper cites Compress to impress: Unleashing the potential of compressive memory in real-world long-term conversations.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Compress to impress: Unleashing the potential of compressive memory in real-world long-term conversations

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.238482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e929c0bd-deb7-439c-af1c-642ee2f7e4f8 · outbound

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

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.619628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4c8e470d-0e4c-45d7-a0ea-1e34854ca47c · outbound

This paper cites Shicheng Fang, Yuxin Wang, Xiaoran Liu, Jiahao Lu, Chuanyuan Tan, Xinchi Chen, Yining Zheng, Xuanjing Huang, and Xipeng Qiu.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Shicheng Fang, Yuxin Wang, Xiaoran Liu, Jiahao Lu, Chuanyuan Tan, Xinchi Chen, Yining Zheng, Xuanjing Huang, and Xipeng Qiu

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.602699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 27c0d6c3-5e6d-46e2-87b4-4c322ddb1709 · outbound

This paper cites Pan, Yuxin Jiang, and Kam-Fai Wong.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Pan, Yuxin Jiang, and Kam-Fai Wong

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.232195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 85c9117d-fe79-40ec-8ed9-0b8084ab9618 · outbound

This paper cites From Local to Global: A Graph RAG Approach to Query-Focused Summarization.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.608146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 26f6211a-9fd5-47f1-a230-82304a5a0ccc · outbound

This paper cites Lightmem: Lightweight and efficient memory-augmented generation.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Lightmem: Lightweight and efficient memory-augmented generation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.235507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 09cb5fa0-d446-48d1-b2ae-3025df7313dc · outbound

This paper cites ReTool: Reinforcement Learning for Strategic Tool Use in LLMs.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.625287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ebb3fe59-dd01-4df3-b1fb-486963511d9d · outbound

This paper cites doi: 10.1038/s41586-025-09422-z.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA doi: 10.1038/s41586-025-09422-z

Reference 8

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.262085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8ee437bb-895f-4f73-84e4-36b99bca2a37 · outbound

This paper cites LightRAG: Simple and fast retrieval-augmented generation.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA LightRAG: Simple and fast retrieval-augmented generation

Reference 9

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.252807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 36f52cf2-e6fc-4a30-91ba-3f39220ca183 · outbound

This paper cites From RAG to memory: Non-parametric continual learning for large language models.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA From RAG to memory: Non-parametric continual learning for large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.277092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7fd0b4df-c4ca-405e-a1c5-1e7a606b6d40 · outbound

This paper cites Memory in the age of AI agents.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Memory in the age of AI agents

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.271097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8305fdd6-ee84-49fe-963e-7e92290261d3 · outbound

This paper cites Memory in the Age of AI Agents.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Memory in the Age of AI Agents

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.555665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d3181dd0-d9a0-4a3f-8142-99b07410ad7d · outbound

This paper cites Rethinking memory mechanisms of foundation agents in the second half.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Rethinking memory mechanisms of foundation agents in the second half

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.582038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aa938dba-804b-41be-8ab3-d3039b35406c · outbound

This paper cites WAGLE: Strategic weight attribution for effective and modular unlearning in large language models.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA WAGLE: Strategic weight attribution for effective and modular unlearning in large language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.274267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4869d813-cdb6-4f95-a749-ab241a2f0183 · outbound

This paper cites an unresolved cited work.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-05-22T07:14:43.311302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c50d466d-475c-4a4f-8d7c-277eede80208 · outbound

This paper cites The AI hippocampus: How far are we from human memory?Transactions on Machine Learning Research.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA The AI hippocampus: How far are we from human memory?Transactions on Machine Learning Research

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.307773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 121e9150-7d3d-4ed2-a67f-21e676c7155d · outbound

This paper cites Graph chain-of-thought: Augmenting large language models by reasoning on graphs.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Graph chain-of-thought: Augmenting large language models by reasoning on graphs

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.352831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 000e768f-95b2-4ea4-9b1c-7d9006e0a1f7 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.613636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ec9f7a7-6581-40da-a172-9268531c3ed2 · outbound

This paper cites Memory OS of AI agent.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Memory OS of AI agent

Reference 19

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.241512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7e93b19c-a793-4a28-9048-f79f83ff6bef · outbound

This paper cites A human-inspired reading agent with gist memory of very long contexts.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA A human-inspired reading agent with gist memory of very long contexts

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.315001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ad9e4dee-8418-4a92-adbc-3077e769074f · outbound

This paper cites Hello again! LLM-powered personalized agent for long-term dialogue.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Hello again! LLM-powered personalized agent for long-term dialogue

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.397485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f4f91aed-b793-4b01-94e8-d427ee99f693 · outbound

This paper cites StructRAG: Boosting knowledge intensive reasoning of LLMs via inference-time hybrid information structurization.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA StructRAG: Boosting knowledge intensive reasoning of LLMs via inference-time hybrid information structurization

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.382850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3b023d38-1459-4e83-918c-0e455b44cf5a · outbound

This paper cites Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang

Reference 23

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.268455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ebc8388a-7004-4ef7-8a51-ca0ebc4a2800 · outbound

This paper cites Evaluating very long-term conversational memory of LLM agents.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Evaluating very long-term conversational memory of LLM agents

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.386301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1b3f97da-5f98-44ed-b665-0754d899882f · outbound

This paper cites Towards lifelong dialogue agents via timeline-based memory management.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Towards lifelong dialogue agents via timeline-based memory management

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.393892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 743f32e2-7b70-4fbd-b5c0-43e70acc702d · outbound

This paper cites URL https://aclanthology.org/2025.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA URL https://aclanthology.org/2025

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.290760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6fd6118d-7133-42c9-bc17-70af9a2f83a9 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA MemGPT: Towards LLMs as Operating Systems

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T07:14:42.586716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4a781d9c-e68e-40b1-a7f8-1584e6f1a429 · outbound

This paper cites Vicky Zhao, Lili Qiu, and Dongmei Zhang.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Vicky Zhao, Lili Qiu, and Dongmei Zhang

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.280404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f1d90ce5-9fe7-42fe-aa09-fcea4e65b7b0 · outbound

This paper cites Vicky Zhao, Lili Qiu, and Jianfeng Gao.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Vicky Zhao, Lili Qiu, and Jianfeng Gao

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.390016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 65c43476-86f6-466d-bae0-549a6c9b4096 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Direct preference optimization: Your language model is secretly a reward model

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.303837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 563ea9fd-3266-44f8-9420-c30f8045af77 · outbound

This paper cites From isolated conversations to hierarchical schemas: Dynamic tree memory representation for LLMs.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA From isolated conversations to hierarchical schemas: Dynamic tree memory representation for LLMs

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.297958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f35adffb-f1a3-4bb1-b135-11c76417fdd3 · outbound

This paper cites Beyond pipelines: A survey of the paradigm shift toward model-native agentic ai.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Beyond pipelines: A survey of the paradigm shift toward model-native agentic ai

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.571472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 52b63478-50d0-4120-ada9-db9a599ec3e7 · outbound

This paper cites Proximal Policy Optimization Algorithms.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Proximal Policy Optimization Algorithms

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.550928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6ec1e76-9f93-487c-b981-d3d1bd41ca31 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.591379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5541c654-2fa8-4701-9043-822dab76bf99 · outbound

This paper cites REMem: Reasoning with episodic memory in language agent.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA REMem: Reasoning with episodic memory in language agent

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.264828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 442462eb-6a84-4179-93eb-0619b3136783 · outbound

This paper cites Enhancing agentic rl with progressive reward shaping and value-based sampling policy optimization.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Enhancing agentic rl with progressive reward shaping and value-based sampling policy optimization

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.597245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation adc74125-a222-4f7b-9ed3-f75116bceb09 · outbound

This paper cites H-MEM: Hierarchical memory for high-efficiency long-term reasoning in LLM agents.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA H-MEM: Hierarchical memory for high-efficiency long-term reasoning in LLM agents

Reference 37

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.256266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 113ff078-094d-44b7-9b2e-320d365caccc · outbound

This paper cites In prospect and retrospect: Reflective memory management for long-term personalized dialogue agents.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA In prospect and retrospect: Reflective memory management for long-term personalized dialogue agents

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.321700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4b7b985b-7a31-44b3-bb66-c57cc6ac159c · outbound

This paper cites URL https://aclanthology.org/2025.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA URL https://aclanthology.org/2025

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.283489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c86ef2ba-e0aa-4ec4-9651-3cc07b621e5c · outbound

This paper cites TRL: Transformers Re- inforcement Learning.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA TRL: Transformers Re- inforcement Learning

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.255245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0a039c99-0b27-4384-a6ae-af3a8fdc773e · outbound

This paper cites Recursively summarizing enables long-term dialogue memory in large language models.Neurocomputing, 639:130193.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Recursively summarizing enables long-term dialogue memory in large language models.Neurocomputing, 639:130193

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.273953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fad69038-f189-40a7-8e64-0d3031d270d8 · outbound

This paper cites Beyond the limits: A survey of techniques to extend the context length in large language models.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Beyond the limits: A survey of techniques to extend the context length in large language models

Reference 42

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.249118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d09889b3-53d1-47c9-bca7-d18e05434008 · outbound

This paper cites Reinforcement learning with verifiable rewards implicitly incentivizes correct reasoning in base LLMs.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Reinforcement learning with verifiable rewards implicitly incentivizes correct reasoning in base LLMs

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.258552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0790ef41-9d8d-4146-b3a7-03130eb40414 · outbound

This paper cites Long- memeval: Benchmarking chat assistants on long-term interactive memory.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Long- memeval: Benchmarking chat assistants on long-term interactive memory

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.318366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8c22e7dc-ca84-4232-8506-dd999ca5a5cd · outbound

This paper cites From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:14:42.566026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 97149ad2-4f0a-4c8e-85fb-3a0e0ea2b094 · outbound

This paper cites DaGRPO: Rectifying gradient conflict in reasoning via distinctiveness-aware group relative policy optimization.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA DaGRPO: Rectifying gradient conflict in reasoning via distinctiveness-aware group relative policy optimization

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.252015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7461bf18-2913-4027-8de2-46d7e68d5b58 · outbound

This paper cites From single to multi- granularity: Toward long-term memory association and selection of conversational agents.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA From single to multi- granularity: Toward long-term memory association and selection of conversational agents

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.248715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cd15d4a9-03c0-450a-8031-7ba62debb3dd · outbound

This paper cites RECOMP: Improving retrieval-augmented LMs with context compression and selective augmentation.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA RECOMP: Improving retrieval-augmented LMs with context compression and selective augmentation

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.261695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cebe6c5f-9f90-4827-9cdd-816cf738090c · outbound

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

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA A-mem: Agentic memory for LLM agents

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.286427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 510e563e-b34f-4d48-a904-967024d11e1e · outbound

This paper cites General agentic memory via deep research.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA General agentic memory via deep research

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.545982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 34689446-ff67-4006-816b-fac4817aa373 · outbound

This paper cites Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Reference 51

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T07:14:42.576513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9c05502d-2c37-4fee-97c0-ae5b93f27659 · outbound

This paper cites DAPO: An open-source LLM reinforcement learning system at scale.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA DAPO: An open-source LLM reinforcement learning system at scale

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.241802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2f88e147-0257-4fe5-87c6-2da701550591 · outbound

This paper cites Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model? InThe Thirty-ninth Annual Conference on Neural Information Processing Systems.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model? InThe Thirty-ninth Annual Conference on Neural Information Processing Systems

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.245220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d01dcc88-5d96-4cb0-9529-5b5809dc369c · outbound

This paper cites The landscape of agentic reinforcement learning for llms: A survey.Transactions on Machine Learning Research, 2026.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA The landscape of agentic reinforcement learning for llms: A survey.Transactions on Machine Learning Research, 2026

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.268187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f4a8eac5-67ec-451c-9d5a-0b8d054f4377 · outbound

This paper cites an unresolved cited work.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-05-22T07:14:43.294208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 39a36bbe-e4e3-41f7-9ea3-61a42cd9406b · outbound

This paper cites Assomem: Scalable memory QA with multi-signal associative retrieval.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Assomem: Scalable memory QA with multi-signal associative retrieval

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.376535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ff7adc53-86d0-4a7a-8096-a3a11eefd621 · outbound

This paper cites Bridging intuitive associations and de- liberate recall: Empowering LLM personal assistant with graph-structured long-term mem- ory.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Bridging intuitive associations and de- liberate recall: Empowering LLM personal assistant with graph-structured long-term mem- ory

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.369604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 61e9f2a5-52cb-4b8d-aa09-78d90bab3cb4 · outbound

This paper cites A survey on the memory mechanism of large language model- based agents.ACM Transactions on Information Systems, 43(6):155:1–155:47.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA A survey on the memory mechanism of large language model- based agents.ACM Transactions on Information Systems, 43(6):155:1–155:47

Reference 58

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.245034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 09837a21-c24a-48ca-9276-02a270c3763b · outbound

This paper cites Adversarial eval.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Adversarial eval

Reference 59

Resolution: verified exact; doi, observed 2026-05-22T07:14:42.265150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fb41c653-b54c-4ad8-a5b5-34659bcf3cd7 · outbound

This paper cites Consider each message one by one.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Consider each message one by one

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.372993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 96467e33-a841-4828-a376-0f45038068de · outbound

This paper cites msg_id" to.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA msg_id" to

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.379974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5f3d49eb-8783-42b4-a00f-6099d9504248 · outbound

This paper cites msg_id" in.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA msg_id" in

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.366222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 58958375-aa3e-481e-86ed-e9476384d6d6 · outbound

This paper cites info" self-contained: - Conduct reference resolution (pronouns, ellipsis, named entities) when the referent is unambiguous in its surrounding context. - Interpret.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA info" self-contained: - Conduct reference resolution (pronouns, ellipsis, named entities) when the referent is unambiguous in its surrounding context. - Interpret

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.400953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d86d5c8a-ae7a-4a1f-b59b-2db768f75160 · outbound

This paper cites education field.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA education field

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.359857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8ab3b701-8b15-4929-9487-348f96dc776f · outbound

This paper cites this message is useful because.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA this message is useful because

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.363105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f378dcb1-400b-4206-b6c5-136579a3e768 · outbound

This paper cites useful_msg.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA useful_msg

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.330683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bc0f174d-6e45-49f0-b291-afd0b4675247 · outbound

This paper cites an unresolved cited work.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-05-22T07:14:43.356560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 092fac47-1424-4ac4-a507-8b60dae3affd · outbound

This paper cites user", "assistant.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA user", "assistant

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:14:43.324420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f65934fb-ff73-4da0-8858-72131fd1620a · outbound

This paper cites an unresolved cited work.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-05-22T07:14:43.327468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a404c475-592e-4b98-878d-f647f5bf14af · outbound

This paper cites I/we/my" are from the perspective of the TARGET MESSAGE’s speaker. -.

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA I/we/my" are from the perspective of the TARGET MESSAGE’s speaker. -

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.561019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers