Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs | Paper Citation Record

Observation 5522e861-a8a9-4dba-98d6-8cdcd6a3b449 · outbound

This paper cites Gpt-5 system card.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Gpt-5 system card

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.643334Z

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 d4f26dd5-899a-43d5-bb22-3ffba4195ff6 · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal intelli- gence.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs The llama 4 herd: The beginning of a new era of natively multimodal intelli- gence

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.639382Z

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 1472877b-77eb-45b5-b274-a22a5c0423a4 · outbound

This paper cites Qwen3 Technical Report.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Qwen3 Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.199394Z

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 e7a849a3-a296-4ca8-86a2-8675c6d56616 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.584766Z

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 d7032d39-2799-4dd7-aa96-b2a198868bcf · outbound

This paper cites TrustLLM: Trustworthiness in Large Language Models.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs TrustLLM: Trustworthiness in Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:17:09.209714Z

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 e5f570a1-8761-4ca2-87b2-16eaaaef9eb7 · outbound

This paper cites OpenAI o1 System Card.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs OpenAI o1 System Card

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.076643Z

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 c65d0d83-dcd0-4cfb-b0bf-91dd860cc313 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.153736Z

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 5d98d0fd-b6d6-4e76-b462-7cce0e5f652c · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Kimi K2: Open Agentic Intelligence

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.124338Z

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 4266b1db-1aad-4bdb-b26b-791ebcb31019 · outbound

This paper cites A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T11:11:18.254256Z

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 3af8b030-38f1-4052-b7f0-ee2c8f86a3f6 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Retrieval-augmented generation for knowledge-intensive nlp tasks

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.575728Z

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 22ae4234-45c5-4ef2-a718-f39125af97dd · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.131734Z

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 ab3052a3-84fb-46bb-8382-bfd75c3e51ff · outbound

This paper cites Introducing deep research.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Introducing deep research

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.483454Z

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 688bacf0-196d-48d0-88d2-4682a5e20f8d · outbound

This paper cites Gemini deep research – your personal research assistant.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Gemini deep research – your personal research assistant

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.554793Z

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 0a5071e2-d99c-4246-b7d8-3408ce814114 · outbound

This paper cites Introducing perplexity deep research.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Introducing perplexity deep research

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.551419Z

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 a19526f1-039f-4269-a1d7-9a97a266df7e · outbound

This paper cites Deep Reinforcement Learning: An Overview.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Deep Reinforcement Learning: An Overview

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.220351Z

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 4e3b49b0-5a79-4fc5-bf8c-00184450c28d · outbound

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

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.231320Z

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 f0ca6996-4c88-494e-87e7-4e3a5b5a3559 · outbound

This paper cites R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.095752Z

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 74f3c35a-f61f-4efb-a4ee-568e19fcdf03 · outbound

This paper cites ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.137585Z

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 c8954da1-60fc-43b4-91cb-061781681a02 · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.148341Z

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 ddc5a5d6-2253-4654-8f7d-1ce9633c1e8f · outbound

This paper cites Musique: Multihop questions via single-hop question composition.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Musique: Multihop questions via single-hop question composition

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.490135Z

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 43168c99-88ac-4736-9b1b-7433bd3e196b · outbound

This paper cites Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.210123Z

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 ba085bd1-dce0-48e0-9ec9-d97a70c7f8e1 · outbound

This paper cites Deep Research Agents: A Systematic Examination And Roadmap.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Deep Research Agents: A Systematic Examination And Roadmap

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.070924Z

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 92a7248f-7939-4dbe-acdd-f2217147c428 · outbound

This paper cites Reinforcement learning foundations for deep research systems: A survey.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Reinforcement learning foundations for deep research systems: A survey

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.160725Z

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 fb0f6d9c-0454-48ba-94c7-c5ebb4f24fc0 · outbound

This paper cites Reinforcement learning: An introduction, volume 1.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Reinforcement learning: An introduction, volume 1

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.479975Z

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 bcc31c79-d875-40af-b99a-e5c851527ffe · outbound

This paper cites Reinforcement learning: A survey.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Reinforcement learning: A survey

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.496232Z

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 0fb80d5e-1fd7-449b-a908-02bc1a97f13f · outbound

This paper cites Agent models: Internalizing Chain-of-Action Generation into Reasoning models.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Agent models: Internalizing Chain-of-Action Generation into Reasoning models

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.178584Z

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 0fcab628-5b5b-4eea-af6c-c1a9c9c9a03d · outbound

This paper cites An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.283961Z

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 8a8749f6-0fad-4c28-b227-8d4485acdae2 · outbound

This paper cites Beyond ten turns: Unlocking long-horizon agentic search with large-scale asynchronous rl.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Beyond ten turns: Unlocking long-horizon agentic search with large-scale asynchronous rl

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.277974Z

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 169d6c5c-414c-4bce-b66a-120a191233e7 · outbound

This paper cites Measuring and Narrowing the Compositionality Gap in Language Models.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Measuring and Narrowing the Compositionality Gap in Language Models

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.204818Z

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 b9e39aa2-fa98-4f6c-979a-b3fb2e413cd2 · outbound

This paper cites All Language Models Large and Small.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs All Language Models Large and Small

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.272302Z

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 a0e2c2ea-fe14-490d-91ea-f5cc5551a909 · outbound

This paper cites Reinforcement learning as heuristic for action-rule preferences.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Reinforcement learning as heuristic for action-rule preferences

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.597757Z

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 ab6fa824-fb78-49ac-93da-b737226b6f4b · outbound

This paper cites Reinforcement learning framework for window hardware installation.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Reinforcement learning framework for window hardware installation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.592232Z

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 56fa5997-eb6b-4eb8-a6f2-81443f103673 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Proximal Policy Optimization Algorithms

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.289884Z

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 eb437cf5-3b5e-4212-9264-0670d1554bc7 · outbound

This paper cites High-Dimensional Continuous Control Using Generalized Advantage Estimation.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.248341Z

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 9d75b404-86cb-4739-a4aa-3cb4d678bd00 · outbound

This paper cites ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.215298Z

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 fe3ef81d-2135-4304-b812-a8ab20d4c57c · outbound

This paper cites ZeroSearch: Incentivize the Search Capability of LLMs without Searching.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.243027Z

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 e1aa069b-9b7b-46a1-aba8-ddf010ed2d6b · outbound

This paper cites R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.237838Z

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 c7c41de9-4fe9-4c31-8288-f52bc1be63bb · outbound

This paper cites SSRL: Self-Search Reinforcement Learning.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs SSRL: Self-Search Reinforcement Learning

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.267234Z

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 8e9fd6de-99b2-4e1f-b9e1-580c3c687b17 · outbound

This paper cites StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.260446Z

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 59c667e9-3d8f-4a65-a37b-c138a590df99 · outbound

This paper cites Qwen2.5 technical report.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Qwen2.5 technical report

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.588576Z

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 48b1a9db-60ea-4af6-b27e-d01b7b24938c · outbound

This paper cites Text Embeddings by Weakly-Supervised Contrastive Pre-training.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Text Embeddings by Weakly-Supervised Contrastive Pre-training

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.226219Z

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 50f0a0b5-41e8-4729-8698-9eb2008ae68a · outbound

This paper cites Dense passage retrieval for open-domain question answering.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Dense passage retrieval for open-domain question answering

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.579882Z

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 698e925b-6bb9-4d9f-a849-1e5c58ca86a2 · outbound

This paper cites DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.188303Z

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 95a35b92-324c-41c0-afe5-153aa7987f46 · outbound

This paper cites O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.194028Z

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 4edd2f95-e2de-4c54-93fe-7b8d4a76f0fc · outbound

This paper cites MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.143270Z

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 44da3697-5f01-4e2f-bd71-eca5deb2ca06 · outbound

This paper cites EvolveSearch: An Iterative Self-Evolving Search Agent.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs EvolveSearch: An Iterative Self-Evolving Search Agent

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.166986Z

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 49995253-25d3-4d8f-8adf-ea7e59401c3f · outbound

This paper cites Dynasearcher: Dynamic knowl- edge graph augmented search agent via multi-reward reinforcement learning.arXiv preprint arXiv:2507.17365.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Dynasearcher: Dynamic knowl- edge graph augmented search agent via multi-reward reinforcement learning.arXiv preprint arXiv:2507.17365

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.173111Z

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 80df2a23-96fa-4d33-a5ef-5582c7155f66 · outbound

This paper cites Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:55.832401Z

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 5bd3d417-cfb6-49ae-8263-e532d53a9dd2 · outbound

This paper cites Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.571459Z

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 4274b44a-aeeb-46d4-81dd-6148880450f4 · outbound

This paper cites Musique: Multihop questions via single-hop question composition.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Musique: Multihop questions via single-hop question composition

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.567578Z

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 4144baa3-ebe0-4588-b4db-b54e73a3d1af · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs HybridFlow: A Flexible and Efficient RLHF Framework

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.084347Z

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 3be489a4-d316-4e85-87c6-12004b738e88 · outbound

This paper cites cheatable.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs cheatable

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:11:18.109682Z

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 e9147bb6-11d3-4ef4-aa3d-61631c60acd6 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.564328Z

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 6187f4d6-eea4-4fc3-b720-4ad127846508 · outbound

This paper cites Frédéric Chopin.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Frédéric Chopin

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.560946Z

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 73e5a1b9-f6d3-4cb8-80a6-d010477ae8c1 · outbound

This paper cites presidential election.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs presidential election

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.557728Z

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 20cee2c4-472d-4dde-b5ac-264b3e3b7889 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.548210Z

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 4b9fd755-9b88-476b-a961-3940243a51a6 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.545184Z

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 5cde93b6-9a10-4745-ac71-4d3423110213 · outbound

This paper cites 2000 United States presidential election.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs 2000 United States presidential election

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.542039Z

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 85f81e82-0e57-45d9-9f79-04b8edf5d734 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.538728Z

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 dd1a9eef-1cf8-4720-9041-18fb7cfb327c · outbound

This paper cites The Road to City A.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs The Road to City A

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.535731Z

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 64a24498-bd34-43d6-b6fc-506052223298 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.532864Z

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 328b5363-f98b-455a-bbe3-ad99969e0847 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.529707Z

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 7196d4c6-5fbc-4f3f-b2d9-96cbf2ecca96 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.526152Z

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 797c1711-0cea-4ed9-90e4-b2fa7466ba50 · outbound

This paper cites United Ireland.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs United Ireland

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.522849Z

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 7d2c87a5-e121-4030-bd6d-8ae05be7f180 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.519527Z

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 4c45e757-b749-48e5-a58c-5aa20c3bdbdc · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.516512Z

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 d8136fd6-12d1-41ae-968e-f8d2ab9a1ae0 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.513734Z

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 07d7e813-ed85-492b-8c12-d29872e7d3d5 · outbound

This paper cites Wellesley, Massachusetts.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Wellesley, Massachusetts

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.510816Z

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 d7b0447c-48a2-4d76-bbe0-fa9fe1acf184 · outbound

This paper cites America-Lite: How Imperial Academia Dismantled Our Culture.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs America-Lite: How Imperial Academia Dismantled Our Culture

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.507430Z

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 3f2b3fca-d731-4c3e-ad07-55bed299e683 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.492882Z

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 5f618c56-0c51-4b4a-b9ac-de7542f3eeaa · outbound

This paper cites America-Lite: How Imperial Academia Dismantled Our Culture.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs America-Lite: How Imperial Academia Dismantled Our Culture

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.504476Z

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 d726adbd-7e76-4b45-a3d1-8108faa3e0ce · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.501551Z

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 2ea9bbe0-ebb7-4283-b316-cd37dc099432 · outbound

This paper cites an unresolved cited work.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-05-18T11:11:19.486514Z

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 16734296-2cec-4cde-abac-d3c34c3e7138 · outbound

This paper cites The Mystic Masseur.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs The Mystic Masseur

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T11:11:19.498835Z

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