Fast, Slow, and Tool-augmented Thinking for LLMs: A Review | Paper Citation Record

Observation ff09a764-c047-43ad-b0d3-009a47b90bb0 · outbound

This paper cites Claude sonnet 4, 2025.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Claude sonnet 4, 2025

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:18.132505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 552aaea7-91a8-4cc3-98c9-278dbe8c3aa4 · outbound

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

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.900417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4226ffbb-0e54-4fa3-a283-65de9b02706a · outbound

This paper cites Openai o3, 2025.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Openai o3, 2025

Reference 3

Resolution: parse uncertain; raw_fallback, observed 2026-08-15T17:30:18.119454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 713bcdfe-bca3-413e-86d0-990c7f2cbdc6 · outbound

This paper cites Grok 4, 2025 18 Front.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Grok 4, 2025 18 Front

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:18.092218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 832bb82b-409e-4725-917b-820c219d9fd6 · outbound

This paper cites From System 1 to System 2: A Survey of Reasoning Large Language Models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review From System 1 to System 2: A Survey of Reasoning Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.924599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3b54eb-fb8d-4016-9401-2a1567d3a690 · outbound

This paper cites Thinking, fast and slow.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Thinking, fast and slow

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:18.067127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6d870133-a2c3-4a6c-b24f-5bd09b644eb7 · outbound

This paper cites DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.938391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d493cdeb-e8dc-445e-a750-b48e90b0de07 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Chain-of-thought prompting elicits reasoning in large language models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:18.048461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2d2578b2-7dcc-4666-ab33-98ecfcc5da4f · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Tree of thoughts: Deliberate problem solving with large language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:18.022619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5c2bb586-c503-4a29-96e2-f8c68ca86ff8 · outbound

This paper cites Towards mitigat- ing llm hallucination via self reflection.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Towards mitigat- ing llm hallucination via self reflection

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:18.001214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ec97284d-8bdf-4f4f-adfa-e34867531bd4 · outbound

This paper cites Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.965543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e462f77-ec6a-4314-84f5-86bbb2f72124 · outbound

This paper cites Let llms break free from overthinking via self-braking tuning.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Let llms break free from overthinking via self-braking tuning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.971154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889f3498-e672-4648-b8b2-8ff8af73f5e3 · outbound

This paper cites Large language models are zero-shot reasoners.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Large language models are zero-shot reasoners

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.981059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation aa125561-5b63-4363-a12b-4e808fef7145 · outbound

This paper cites Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.980677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d6cd12f-e9b3-4ba1-95f2-a0239ef4f106 · outbound

This paper cites Confident adaptive language modeling, 2022.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Confident adaptive language modeling, 2022

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.952624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c5bd9a8b-ac94-4785-9cd2-69af138a75d9 · outbound

This paper cites How Much Knowledge Can You Pack Into the Parameters of a Language Model?.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review How Much Knowledge Can You Pack Into the Parameters of a Language Model?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.990969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a387785a-cec3-4c41-912b-bcac1bb0a496 · outbound

This paper cites Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:14.996129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be76d43e-b2b9-418c-b9cc-6f3a949f8122 · outbound

This paper cites Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.002214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6d5c3b4-79d0-4b14-8d51-eedc867cf139 · outbound

This paper cites AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.007966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 240d782d-3b55-4c59-abe5-b27d8e3076b2 · outbound

This paper cites ThinkSwitcher: When to Think Hard, When to Think Fast.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review ThinkSwitcher: When to Think Hard, When to Think Fast

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.014240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 383c6214-7f2b-4e38-81c1-bf3aac211492 · outbound

This paper cites Active retrieval augmented generation.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Active retrieval augmented generation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.938728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 946c80a6-b9cd-44c1-ab81-cc658b914795 · outbound

This paper cites MUR: Momentum Uncertainty guided Reasoning for Large Language Models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review MUR: Momentum Uncertainty guided Reasoning for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.027213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb0ae3a-2a2d-4c59-9334-fbdaddebec3e · outbound

This paper cites AdaptThink: Reasoning Models Can Learn When to Think.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review AdaptThink: Reasoning Models Can Learn When to Think

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.033601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed3f5221-897a-493b-8f5b-3c5d9e2536bf · outbound

This paper cites Learning when to think: Shaping adaptive reasoning in r1-style models via multi-stage rl.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Learning when to think: Shaping adaptive reasoning in r1-style models via multi-stage rl

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.049378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cf24f94-c722-433f-b755-a069ceb7b55f · outbound

This paper cites Certainty- guided reasoning in large language models: A dy- namic thinking budget approach.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Certainty- guided reasoning in large language models: A dy- namic thinking budget approach

Reference 25

Resolution: verified exact; raw_fallback, observed 2026-08-15T17:30:17.130788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 61c5285b-82c6-4e94-9b7a-a7a9e115980b · outbound

This paper cites Dynamic early exit in reasoning models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Dynamic early exit in reasoning models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.066040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 732163e2-907a-4fe9-8b7d-28a7eb5d9437 · outbound

This paper cites Seakr: Self-aware knowledge retrieval for adaptive re- trieval augmented generation, 2024.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Seakr: Self-aware knowledge retrieval for adaptive re- trieval augmented generation, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.918182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dc5ac0d0-3617-4690-b8c2-817a0a35cb59 · outbound

This paper cites Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.088590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8beb8853-7002-4f1b-9aa0-8fc33063b790 · outbound

This paper cites Adaptive Retrieval-Augmented Generation for Conversational Systems.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Adaptive Retrieval-Augmented Generation for Conversational Systems

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.097373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c2e1ef6-d642-4ab4-9481-aa824df0965a · outbound

This paper cites Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.104326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edc94ff2-62e4-4415-a9e6-a39f0afa4eae · outbound

This paper cites Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.115165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c844d42a-b1ab-415e-970d-c048b7d29704 · outbound

This paper cites Sugar: Leveraging contextual confidence for smarter retrieval.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Sugar: Leveraging contextual confidence for smarter retrieval

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.895994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5fcee4ca-8534-42a0-ab2b-d0f1754a5c05 · outbound

This paper cites Smart: Select, mix, and reinvent–a strategy fusion framework for llm-driven reasoning and planning.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Smart: Select, mix, and reinvent–a strategy fusion framework for llm-driven reasoning and planning

Reference 33

Resolution: verified exact; raw_fallback, observed 2026-08-15T17:30:16.826247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 764b5ffd-56b4-4300-88ac-287235c405a1 · outbound

This paper cites Metacognition and cognitive monitoring: A new area of cognitive–developmental inquiry.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Metacognition and cognitive monitoring: A new area of cognitive–developmental inquiry

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.869445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2d8462a3-bb64-4eaf-9f6a-706d1e821c3f · outbound

This paper cites Cognitive load during problem solving: Ef- fects on learning.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Cognitive load during problem solving: Ef- fects on learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.847726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7c9008a5-4297-4fca-b570-39ce6411b1fd · outbound

This paper cites Au- tol2s: Auto long-short reasoning for efficient large lan- guage models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Au- tol2s: Auto long-short reasoning for efficient large lan- guage models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.164128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3d37547-4a5b-497f-a0ae-c1ae225d5f7a · outbound

This paper cites TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.172885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f4d181-39c5-438a-aa24-af6d374543fe · outbound

This paper cites Self-rag: Learning to retrieve, generate, and critique through self- reflection.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Self-rag: Learning to retrieve, generate, and critique through self- reflection

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.828810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 31c5e29b-56ac-4707-9761-d1a575bf698a · outbound

This paper cites Toolformer: Language models can teach themselves to use tools,.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Toolformer: Language models can teach themselves to use tools,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.811929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 47a2e2f1-9f53-444e-af46-4c9a2d928475 · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review WebGPT: Browser-assisted question-answering with human feedback

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.199373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c67a906f-54f4-44dd-aff6-52ddf77274ad · outbound

This paper cites SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.205064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c766f8fe-5705-44fa-95bb-0a6a60ef32cd · outbound

This paper cites KAT-V1: Kwai-AutoThink Technical Report.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review KAT-V1: Kwai-AutoThink Technical Report

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.213229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 793d3e35-8b91-4ef3-b08a-cc09ef430e5f · outbound

This paper cites Think Only When You Need with Large Hybrid-Reasoning Models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Think Only When You Need with Large Hybrid-Reasoning Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.221305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0e3ea3d-8a07-4d48-9bce-b32ab1516d74 · outbound

This paper cites To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.231150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae88453-6078-4f73-a392-bcde0c42eeb6 · outbound

This paper cites Exaone 4.0: Unified large language models integrating non-reasoning and reasoning modes.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Exaone 4.0: Unified large language models integrating non-reasoning and reasoning modes

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.237530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f32d73a-e930-477e-bab5-725d8cec00a5 · outbound

This paper cites Introducing gpt-5, 2025.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Introducing gpt-5, 2025

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.795090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0754e023-b2e1-4247-a49f-902780ee0307 · outbound

This paper cites Thinking with nothinking calibration: A new in-context learn- ing paradigm in reasoning large language models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Thinking with nothinking calibration: A new in-context learn- ing paradigm in reasoning large language models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.248508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df0e0bd2-cc61-4afb-b3ce-008d7b53b06b · outbound

This paper cites Z1: Efficient Test-time Scaling with Code.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Z1: Efficient Test-time Scaling with Code

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.254325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b98454b-e23b-4ff2-974e-c72b985d375e · outbound

This paper cites Qwen3 Technical Report.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Qwen3 Technical Report

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.259398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f981b5a6-a7ab-4ac7-8108-9cb9e198e49e · outbound

This paper cites Llama-nemotron: Efficient reasoning models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Llama-nemotron: Efficient reasoning models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.425474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd083e37-5bd3-4bb2-956d-fa95ba797434 · outbound

This paper cites Active retrieval augmented gener- ation.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Active retrieval augmented gener- ation

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.772766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation db44638d-e195-45ab-a516-d0d2d9ad8ff2 · outbound

This paper cites The Web Can Be Your Oyster for Improving Large Language Models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review The Web Can Be Your Oyster for Improving Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.435343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23a87475-4019-4829-9e38-f5bb552ec1fe · outbound

This paper cites Dragin: Dynamic retrieval augmented generation based on the information needs of large language models, 2024.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Dragin: Dynamic retrieval augmented generation based on the information needs of large language models, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.750615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 06f07489-0fab-43eb-9e3e-27cbb7065efb · outbound

This paper cites Retrieve only when it needs: Adaptive retrieval augmentation for hallucination mitigation in large language models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Retrieve only when it needs: Adaptive retrieval augmentation for hallucination mitigation in large language models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.448401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f92bfe05-70f8-4195-8e95-ca6c4f95c2d5 · outbound

This paper cites Alignment for Efficient Tool Calling of Large Language Models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Alignment for Efficient Tool Calling of Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.454533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b4168ad-d30e-4632-8ce9-c43be50bc6e1 · outbound

This paper cites Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.462243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4bc4391-9595-48e4-a955-25329afee8ea · outbound

This paper cites To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.469277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04e057bc-c912-40fa-a36c-3ad442ca3065 · outbound

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

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.475689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05547741-65f9-448a-a00f-e359785c32f4 · outbound

This paper cites R3-rag: Learning step-by- step reasoning and retrieval for llms via reinforcement 20 Front.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review R3-rag: Learning step-by- step reasoning and retrieval for llms via reinforcement 20 Front

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.482356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f47b135f-f8e2-4707-bbcf-6486c1df40d9 · outbound

This paper cites Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.488642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87f1e1b-a5b5-419f-aad1-0f8945e254a8 · outbound

This paper cites Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.498437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 957d8ca2-dd1d-4640-80cb-02dd919e8fe3 · outbound

This paper cites Confidence in the reasoning of large language models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Confidence in the reasoning of large language models

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.717557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6ffd7c16-46fb-47e4-bdf8-e555046a5dd5 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.517612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03345335-0831-4818-817f-2f0e5b0c9b89 · outbound

This paper cites Wizardlm: Empowering large pre- trained language models to follow complex instructions.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Wizardlm: Empowering large pre- trained language models to follow complex instructions

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.697159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4d84c411-6f2f-4454-850b-4e153cf46648 · outbound

This paper cites Gaia: a benchmark for general ai assistants, 2023.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Gaia: a benchmark for general ai assistants, 2023

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.674699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 46abfb34-7d9e-4216-b8b7-fcc9bdf245bb · outbound

This paper cites When do llms need retrieval augmentation? mitigating llms’ overconfidence helps retrieval augmentation.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review When do llms need retrieval augmentation? mitigating llms’ overconfidence helps retrieval augmentation

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.648945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 79704caa-8239-40dc-a548-246fa479ba51 · outbound

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

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.625979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f1831148-bffe-49e1-8b0b-9e9d785f33c9 · outbound

This paper cites The real barrier to llm agent usability is agentic roi.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review The real barrier to llm agent usability is agentic roi

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.566020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea06b70d-32af-4312-b846-5df2adb5535d · outbound

This paper cites Multi-Agent Collaboration Mechanisms: A Survey of LLMs.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.572894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98bfec03-bf39-4c7b-9c9e-8333448608d1 · outbound

This paper cites The interaction between text modality and the learner’s modality preference influ- ences comprehension and cognitive load.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review The interaction between text modality and the learner’s modality preference influ- ences comprehension and cognitive load

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:30:17.598455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fac1af7e-6c2d-4094-96fa-39b6da72ebe9 · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools.

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review Toolformer: Language Models Can Teach Themselves to Use Tools

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T17:30:15.191692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers