Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration | Paper Citation Record

Observation 9987c547-3a84-4242-903d-9cf38d159151 · outbound

This paper cites WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-15T22:43:35.479641Z

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 c14ae87d-840d-4b97-af62-f824bc72ab98 · outbound

This paper cites WebWalker: Benchmarking LLMs in Web Traversal.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration WebWalker: Benchmarking LLMs in Web Traversal

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:10:23.405556Z

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 5927d826-f8ad-40fe-9b36-f282f87c7747 · outbound

This paper cites Qwen3 Technical Report.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Qwen3 Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:10:23.513889Z

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 4ffcccc2-aeab-4d5a-9454-91c30d52c195 · outbound

This paper cites Seed-oss open-source models.https://github.com/ByteDance-Seed/seed-oss.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Seed-oss open-source models.https://github.com/ByteDance-Seed/seed-oss

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.630014Z

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 dbd63f9e-d63d-4aa8-9140-287f1e5f4eff · outbound

This paper cites Qwen3 technical report.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Qwen3 technical report

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.633823Z

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 956be0d3-309d-422f-ae0c-a889821bf62c · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:10:23.427351Z

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 f1a73f88-48e1-40b8-853f-cd1e445be621 · outbound

This paper cites A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:23:15.948876Z

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 b639b585-52a5-489f-ad70-58b2abc530b3 · outbound

This paper cites Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-12T16:44:08.223014Z

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 e117de84-062a-4d2d-9564-f3c49056d95b · outbound

This paper cites Cogito, ergo ludo: An agent that learns to play by reasoning and planning.arXiv preprint arXiv:2509.25052, 2025b.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Cogito, ergo ludo: An agent that learns to play by reasoning and planning.arXiv preprint arXiv:2509.25052, 2025b

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.488892Z

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 06ceceb9-7280-4be3-bd3a-eb5c6a0c7557 · outbound

This paper cites Self-Supervised Prompt Optimization.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Self-Supervised Prompt Optimization

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.492931Z

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 dcce4d15-6ae0-4bf0-9fa1-e067566a0210 · outbound

This paper cites AgentSquare: Automatic LLM Agent Search in Modular Design Space.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration AgentSquare: Automatic LLM Agent Search in Modular Design Space

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.430752Z

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 cdc7e488-c35f-424b-a262-d0e067529dd5 · outbound

This paper cites LLM-AutoDiff: Auto-Differentiate Any LLM Workflow.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration LLM-AutoDiff: Auto-Differentiate Any LLM Workflow

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:10:23.505093Z

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 3ee8dd9d-6854-4cd6-b9f9-2a2dbd5e64d8 · outbound

This paper cites ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:42:50.464031Z

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 662956d9-6f95-4658-95b3-911ec4ab7f15 · outbound

This paper cites MemEvolve: Meta-Evolution of Agent Memory Systems.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration MemEvolve: Meta-Evolution of Agent Memory Systems

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-15T22:18:15.377574Z

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 ceb3aabb-b435-497d-bc62-28752b1c4be3 · outbound

This paper cites Expel: Llm agents are experiential learners.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Expel: Llm agents are experiential learners

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.637560Z

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 01e52578-8665-4e3a-9c1e-48f3b390e376 · outbound

This paper cites Autoguide: Automated generation and selection of state-aware guidelines for large language model agents.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Autoguide: Automated generation and selection of state-aware guidelines for large language model agents

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.622496Z

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 79c62f3d-2616-43fc-a395-4b189b0be422 · outbound

This paper cites A-MEM: Agentic Memory for LLM Agents.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration A-MEM: Agentic Memory for LLM Agents

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:47:29.054201Z

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 8b112bc3-88b0-4f4b-9966-0327c1cd6161 · outbound

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

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:10:49.561366Z

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 32b0ea56-4b4c-40ba-8354-ee0b55937d18 · outbound

This paper cites Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-16T04:41:03.163713Z

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 c0f7519b-80d9-4900-aad4-f6c105090e24 · outbound

This paper cites SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-14T19:35:55.589248Z

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 8e08c3d4-49bc-47e3-85a1-d889b57b9c05 · outbound

This paper cites From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.497270Z

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 d9f8a8ca-5035-4450-912d-7044c6f54ea2 · outbound

This paper cites ToolGen: Unified Tool Retrieval and Calling via Generation.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration ToolGen: Unified Tool Retrieval and Calling via Generation

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.375986Z

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 0dd1f92d-876a-4411-bec9-2be34833247e · outbound

This paper cites Agent Learning via Early Experience.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Agent Learning via Early Experience

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

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 112e82ec-4649-46d1-bbc9-c81e6ce1c8d7 · outbound

This paper cites WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.463113Z

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 0ca00ec7-4d2a-4e55-9fcd-e12388adae42 · outbound

This paper cites AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.451741Z

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 c5e44bd2-d50e-4964-b7d9-a0d1b125defe · outbound

This paper cites RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:13:34.687091Z

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 f34256b5-d1c3-4530-a970-0f95b022aaca · outbound

This paper cites Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.455390Z

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 20cf6747-81f8-4cc0-b435-2a0115ac8bf7 · outbound

This paper cites WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:10:23.472158Z

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 f72d902f-f82e-445b-88b4-4500d7bcc4df · outbound

This paper cites Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:10:23.484189Z

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 4fb95ba2-e076-4cac-beab-8f23ec107d44 · outbound

This paper cites Spice: Self-play in corpus environments improves reasoning.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Spice: Self-play in corpus environments improves reasoning

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.381309Z

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 fb71f621-e6c8-4b55-ae8b-dba0204d34ac · outbound

This paper cites R-Zero: Self-Evolving Reasoning LLM from Zero Data.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration R-Zero: Self-Evolving Reasoning LLM from Zero Data

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-14T19:23:29.765778Z

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 c40d748a-1a6a-45f1-b923-dca4511200a7 · outbound

This paper cites Self-Challenging Language Model Agents.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Self-Challenging Language Model Agents

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.528665Z

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 b784f6f3-78d9-4dde-b611-bb52576ec7e8 · outbound

This paper cites RLSR: Reinforcement Learning from Self Reward.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration RLSR: Reinforcement Learning from Self Reward

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:10:23.385138Z

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 7c6352e8-f8e1-4f74-bb39-cd9da20a8999 · outbound

This paper cites Dr. Zero: Self-Evolving Search Agents without Training Data.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Dr. Zero: Self-Evolving Search Agents without Training Data

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-22T03:22:03.468610Z

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 82ab8871-8a53-437e-80f6-67f5ea3fd3c1 · outbound

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

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Test-time training with self-supervision for generalization under distribution shifts

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.597526Z

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 939b283f-c44a-4a6f-9de8-66075a7d0af4 · outbound

This paper cites ATLAS: Learning to Optimally Memorize the Context at Test Time.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration ATLAS: Learning to Optimally Memorize the Context at Test Time

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.480004Z

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 874e0c24-2587-4a71-88a0-93625cf750da · outbound

This paper cites Titans: Learning to Memorize at Test Time.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Titans: Learning to Memorize at Test Time

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:08:15.778565Z

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 61b4941e-a2eb-4f7d-94a6-c6c9ad753b08 · outbound

This paper cites arXiv preprint arXiv:2512.24695 , year=.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration arXiv preprint arXiv:2512.24695 , year=

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.394732Z

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 58c25473-602a-4c5c-aaf7-23436528b467 · outbound

This paper cites Learning to (Learn at Test Time): RNNs with Expressive Hidden States.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:20:12.625336Z

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 04b2e987-b6ec-4e41-95a6-d3c2f25f8008 · outbound

This paper cites With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.370274Z

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 4b1c9e7b-606c-4e76-9206-6aa4c7b3e169 · outbound

This paper cites Test-Time Training with KV Binding Is Secretly Linear Attention.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Test-Time Training with KV Binding Is Secretly Linear Attention

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:10:23.390076Z

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 93921f84-0d4b-4461-9eba-c54a805fa90a · outbound

This paper cites Locas: Your models are principled initializers of locally-supported parametric memories.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Locas: Your models are principled initializers of locally-supported parametric memories

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.537277Z

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 8c8461f9-393c-4608-9713-a5662f24200b · outbound

This paper cites Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.467718Z

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 60c42b99-93bb-4f17-9b2a-f1923f7ff9c3 · outbound

This paper cites Test-Time Learning for Large Language Models.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Test-Time Learning for Large Language Models

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:10:23.437950Z

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 7ea67f49-1638-48a8-a956-4cb00ac93677 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Efficient memory management for large language model serving with pagedattention

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.544228Z

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 bd6beac7-a794-4e22-86a3-63b8b663881a · outbound

This paper cites Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.608333Z

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 2b57d1bc-1841-4ffc-a430-540c486ca2cd · outbound

This paper cites Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-10T12:10:23.410135Z

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 2501b603-95ae-4d8c-a412-3444d69b1b1c · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Qwen2.5: A party of foundation models, September 2024

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.615015Z

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 ab100d05-7a66-4adc-8e9e-67de88882312 · outbound

This paper cites gpt-oss-120b and gpt-oss-20b model card.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration gpt-oss-120b and gpt-oss-20b model card

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.590859Z

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 393c8e84-5ab1-4fe2-9b43-4cda744dad59 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Kimi K2: Open Agentic Intelligence

Reference 50

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T17:49:28.234076Z

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 0d6c6fcb-0e11-416f-98df-b0e2d073817b · outbound

This paper cites Feel free to choose any category that seems underdeveloped or has interesting URLs you haven’t explored yet.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Feel free to choose any category that seems underdeveloped or has interesting URLs you haven’t explored yet

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.577891Z

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 66b87b25-1d12-4804-ab2f-8d9b53b7cafd · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.584824Z

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 be7619ac-8580-4da6-b1fd-761d2aad5bf3 · outbound

This paper cites Please rely on the actual webpage content to inspire your expansion and ensure accuracy.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Please rely on the actual webpage content to inspire your expansion and ensure accuracy

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.570079Z

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 c6470a4c-acf3-4f37-8d7e-8d2fbf6e2096 · outbound

This paper cites You can expand summaries, add new page entries, or provide deeper insights to make the section richer and more comprehensive.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration You can expand summaries, add new page entries, or provide deeper insights to make the section richer and more comprehensive

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.566494Z

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 34d3c242-89b7-4eff-a399-a2e72e4a6127 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.562047Z

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 176fa36e-3c89-4ec3-915c-d787f0176794 · outbound

This paper cites Continue this exploration process until your guidebook reaches at least{min_token}tokens.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Continue this exploration process until your guidebook reaches at least{min_token}tokens

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.573942Z

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 f16c0a29-8118-4c8b-bdba-d9bc90b9e5ad · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.625858Z

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 a2a194c1-23f9-40d9-b412-d44d94ac72f3 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.648018Z

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 96babc0c-5e11-4181-a351-15ffde95257f · outbound

This paper cites Repeat until all categories are done.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Repeat until all categories are done

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.662219Z

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 b3f85665-9d0f-41db-831c-d867fdfaebf0 · outbound

This paper cites If it exceeds {token_limit}, compress verbose sections withrewrite_category_section().

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration If it exceeds {token_limit}, compress verbose sections withrewrite_category_section()

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.539974Z

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 52f7dd9d-b83f-4472-8836-d4534bf03178 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.651497Z

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 71e57e94-1c54-4ed9-91a7-bdc25a6f3674 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.547728Z

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 b235c5d9-f83c-4bae-b306-0d675ff11594 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.640872Z

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 fd8eb59d-4cd6-4b22-ad41-272272998251 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.604719Z

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 79ae878d-7290-402c-9509-c52442384ef0 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.558664Z

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 3f573d24-0b0d-4c1d-b78a-8410e19e9e02 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.536029Z

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 351bdc7b-7cf4-44d2-a676-ce1ad58446b3 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.555065Z

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 ccdfe041-528d-4f90-8a68-ae1cb642b913 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.528844Z

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 bbfefa89-6bcb-4a11-bf45-8a4c089eff42 · outbound

This paper cites Evaluation rules.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Evaluation rules

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.581469Z

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 d0c9c27e-c400-4fbc-9f6d-fe525f7fe2f4 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.587623Z

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 375cfe5f-405c-4b2f-af46-98c3ef0d5366 · outbound

This paper cites Do NOT assume missing information.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Do NOT assume missing information

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.532431Z

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 bf39d9e4-135c-4457-923e-5d74c286901f · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.593973Z

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 3b898a50-bb3d-47c3-9db2-79c983262460 · outbound

This paper cites Missing any part leads to NOT SUCCESS.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Missing any part leads to NOT SUCCESS

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.618740Z

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 ecbb0a0c-afc7-4239-9801-c92a676f3cd7 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.611288Z

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 438933b1-cc71-4fe6-a051-bd07cef1ddd4 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.601411Z

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 d7a22fde-addd-4b6c-bd37-e334106b7f81 · outbound

This paper cites Instructions:You should briefly explain your reasoning before giving the final verdict.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Instructions:You should briefly explain your reasoning before giving the final verdict

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.551653Z

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 658b7f15-dee3-415a-94e9-d44da434fca7 · outbound

This paper cites an unresolved cited work.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-05-22T03:56:02.520800Z

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 649bee9c-9171-41e4-9714-66b2ec88bc0c · outbound

This paper cites content summary.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration content summary

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.525336Z

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 1d32b665-8878-4ae6-9145-717d6996dc51 · outbound

This paper cites content summary.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration content summary

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.644185Z

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 41de6431-8acb-43d0-a534-924bed26e4d0 · outbound

This paper cites About Us - Team Introduction.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration About Us - Team Introduction

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.654833Z

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 2300fff7-852e-4bad-a06e-8613b565da7c · outbound

This paper cites In this case, you must decide to return to the [Main Page URL] to start looking for new clues from scratch.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration In this case, you must decide to return to the [Main Page URL] to start looking for new clues from scratch

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T03:56:02.658669Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers