Paper Citation Record · LEDGER

Large Language Models Think Too Fast To Explore Effectively

As of 10 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 4 inbound Pith citation observations for arXiv:2501.18009.

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

pith.paper-citation-record.v1
2501.18009 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T01:09:03.186224Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T04:32:30.453762Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T05:57:41.552773Z

Reference resolution

41 of 41 outbound references displayed

verified exact2
verified fuzzy16
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation eb44d2eb-364c-455e-a4b1-ad6895aafccd · outbound

This paper cites Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning.

Large Language Models Think Too Fast To Explore Effectively Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-10T01:09:03.296744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0f6e2654-c4ef-421d-82e1-fb7c685fe827 · outbound

This paper cites How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds.

Large Language Models Think Too Fast To Explore Effectively How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.080868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9965408-97e3-4fe4-af97-fa2bed07f9fd · outbound

This paper cites Using cognitive psychology to understand gpt-3.

Large Language Models Think Too Fast To Explore Effectively Using cognitive psychology to understand gpt-3

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.466854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 763eae38-03a3-4aba-81e3-a260273a94b2 · outbound

This paper cites R-max-a general polynomial time algorithm for near-optimal reinforcement learning.

Large Language Models Think Too Fast To Explore Effectively R-max-a general polynomial time algorithm for near-optimal reinforcement learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.456926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9eec93f8-c90a-4047-8ab8-b0b94ffee8b2 · outbound

This paper cites Empowerment contributes to exploration behaviour in a creative video game.

Large Language Models Think Too Fast To Explore Effectively Empowerment contributes to exploration behaviour in a creative video game

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.448720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cf44b9c5-19f7-4d57-afb5-ab2f39d4af31 · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Large Language Models Think Too Fast To Explore Effectively Towards monosemanticity: Decomposing language models with dictionary learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.093864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcbe40b3-5cb3-44f7-9fb2-4a996caf5ff6 · outbound

This paper cites Exploration by Random Network Distillation.

Large Language Models Think Too Fast To Explore Effectively Exploration by Random Network Distillation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.097191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51a2acd4-4494-481f-978e-7c9adcf5a095 · outbound

This paper cites Cortical substrates for exploratory decisions in humans.

Large Language Models Think Too Fast To Explore Effectively Cortical substrates for exploratory decisions in humans

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.438028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5392d7aa-c6f4-43d1-b3fe-4c31f5058654 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

Large Language Models Think Too Fast To Explore Effectively Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.102779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba6fb529-0c7c-4a61-a69b-db6ab19120b4 · outbound

This paper cites Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models.

Large Language Models Think Too Fast To Explore Effectively Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.105376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ced3f5fc-313a-4cc5-822a-ec16dbfde2d1 · outbound

This paper cites First return, then explore.

Large Language Models Think Too Fast To Explore Effectively First return, then explore

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.108896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d3e7504-e756-4a18-8f83-3e483a3ea265 · outbound

This paper cites Trait somatic anxiety is associated with reduced directed exploration and underestimation of uncertainty.Nature Human Behaviour, 7(1):102–113, 2023.

Large Language Models Think Too Fast To Explore Effectively Trait somatic anxiety is associated with reduced directed exploration and underestimation of uncertainty.Nature Human Behaviour, 7(1):102–113, 2023

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.422043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 726e8a15-2434-4737-aa1f-76f038d988ea · outbound

This paper cites Minedojo: Building open-ended embodied agents with internet-scale knowledge.

Large Language Models Think Too Fast To Explore Effectively Minedojo: Building open-ended embodied agents with internet-scale knowledge

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.113474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad5e94b9-6e83-475b-ac8e-dc2034019f16 · outbound

This paper cites LLaMA Rider: Spurring Large Language Models to Explore the Open World.

Large Language Models Think Too Fast To Explore Effectively LLaMA Rider: Spurring Large Language Models to Explore the Open World

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-10T01:09:03.268260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e1a2e7ff-ee6a-4a50-928a-408bbc0f152a · outbound

This paper cites Deconstructing the human algorithms for exploration.

Large Language Models Think Too Fast To Explore Effectively Deconstructing the human algorithms for exploration

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.409824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f646d2d9-f1d4-46e3-a408-bc6d8100c039 · outbound

This paper cites Reinforcement learning: A survey.

Large Language Models Think Too Fast To Explore Effectively Reinforcement learning: A survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.121367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31d826d5-7db4-48db-b179-9919e6213feb · outbound

This paper cites Can large language models explore in-context?.

Large Language Models Think Too Fast To Explore Effectively Can large language models explore in-context?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.124230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c3a197a-5506-4185-a031-2be35b39f2a7 · outbound

This paper cites The Llama 3 Herd of Models.

Large Language Models Think Too Fast To Explore Effectively The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.127804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8f26483-fa44-447f-8837-5335f798a3f7 · outbound

This paper cites Sparse autoencoder.

Large Language Models Think Too Fast To Explore Effectively Sparse autoencoder

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.398242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation df3e06e4-8f88-4a78-a2ae-b32c7dc623f3 · outbound

This paper cites EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration.

Large Language Models Think Too Fast To Explore Effectively EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.133137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f03fb68d-d8ed-4e75-b772-e41361b08504 · outbound

This paper cites Gpt-4o system card.

Large Language Models Think Too Fast To Explore Effectively Gpt-4o system card

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.390541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 84211f5d-33ac-4d31-ba8e-fed898400cf9 · outbound

This paper cites Openai o1 system card.

Large Language Models Think Too Fast To Explore Effectively Openai o1 system card

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.383923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a192a46d-8e53-4128-a15a-f1da6769422c · outbound

This paper cites Deep exploration via bootstrapped dqn.

Large Language Models Think Too Fast To Explore Effectively Deep exploration via bootstrapped dqn

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.376734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 631083e2-1846-46a5-8da7-a53fa8db9947 · outbound

This paper cites (more) efficient reinforcement learning via posterior sampling.

Large Language Models Think Too Fast To Explore Effectively (more) efficient reinforcement learning via posterior sampling

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.143915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57399b24-7b86-48e8-bdec-89078d078863 · outbound

This paper cites Curiosity-driven exploration by self-supervised prediction.

Large Language Models Think Too Fast To Explore Effectively Curiosity-driven exploration by self-supervised prediction

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.145957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22109a8a-0872-486e-977c-c6b53990fd08 · outbound

This paper cites Planning to explore via self-supervised world models.

Large Language Models Think Too Fast To Explore Effectively Planning to explore via self-supervised world models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.148868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce9360c-3a80-46a8-a8bb-d903209b1af8 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Large Language Models Think Too Fast To Explore Effectively Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.150762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f587d81-fb37-4199-b627-ade6122e4b55 · outbound

This paper cites Uncertainty and exploration in a restless bandit problem.

Large Language Models Think Too Fast To Explore Effectively Uncertainty and exploration in a restless bandit problem

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.355992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 08401066-73b3-47b5-a8d8-fa86203acb8a · outbound

This paper cites Testing theory of mind in large language models and humans.

Large Language Models Think Too Fast To Explore Effectively Testing theory of mind in large language models and humans

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.348262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 74d5b198-7bd2-4140-a98e-2ce793934a59 · outbound

This paper cites Reinforcement learning: An introduction.

Large Language Models Think Too Fast To Explore Effectively Reinforcement learning: An introduction

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.157535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fcab1a9-bcfc-4eb8-a8d7-3357f319fbaf · outbound

This paper cites GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspective.

Large Language Models Think Too Fast To Explore Effectively GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspective

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.160002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29ad2f66-10a0-4326-9125-cd18da858958 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

Large Language Models Think Too Fast To Explore Effectively Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.162626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6835e8e-5c8c-4a27-a2ab-234c5c5a2a6c · outbound

This paper cites Emergent analogical reasoning in large language models.

Large Language Models Think Too Fast To Explore Effectively Emergent analogical reasoning in large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.165299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 115ef107-bf98-4814-8fa4-8466e74bc6ca · outbound

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

Large Language Models Think Too Fast To Explore Effectively Chain-of-thought prompting elicits reasoning in large language models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.167708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2a07405-5492-4385-a4af-e5f061b860ec · outbound

This paper cites Deep exploration as a unifying account of explore-exploit behavior.

Large Language Models Think Too Fast To Explore Effectively Deep exploration as a unifying account of explore-exploit behavior

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.328890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cb2158d4-a2c8-470c-9d3b-22d796a93c68 · outbound

This paper cites Balancing exploration and exploitation with information and randomization.

Large Language Models Think Too Fast To Explore Effectively Balancing exploration and exploitation with information and randomization

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.321009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1635fd9c-ec88-4bb6-afbe-f01b3fd9e088 · outbound

This paper cites Humans use directed and random exploration to solve the explore–exploit dilemma.

Large Language Models Think Too Fast To Explore Effectively Humans use directed and random exploration to solve the explore–exploit dilemma

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.313104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4a41a0fe-c325-4065-a747-3b976432ab29 · outbound

This paper cites Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models.

Large Language Models Think Too Fast To Explore Effectively Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.177968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b8179e8-8448-4f52-aa77-1a861e57979b · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Large Language Models Think Too Fast To Explore Effectively ReAct: Synergizing Reasoning and Acting in Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.180680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0007626a-94a0-478c-9dfd-a5bd9f209ee2 · outbound

This paper cites Counting to Explore and Generalize in Text-based Games.

Large Language Models Think Too Fast To Explore Effectively Counting to Explore and Generalize in Text-based Games

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T01:09:03.183501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48ae509c-b699-45dd-95e0-9ccf74f47c1b · outbound

This paper cites empowerment.

Large Language Models Think Too Fast To Explore Effectively empowerment

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T01:09:03.305205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation 972e99e2-a77d-4d0d-a013-04f2956cd457 · inbound

An Auditable Agent Platform For Automated Molecular Optimisation cites this paper.

An Auditable Agent Platform For Automated Molecular Optimisation Large Language Models Think Too Fast To Explore Effectively

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-06T04:32:30.453762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48b77fdc-7ca7-4255-b2a0-50b6eae0c8fa · inbound

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation cites this paper.

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation Large Language Models Think Too Fast To Explore Effectively

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:25:58.103559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ea21c4d0-dbad-4f3f-ac34-a06c413c579f · inbound

What Do Evolutionary Coding Agents Evolve? cites this paper.

What Do Evolutionary Coding Agents Evolve? Large Language Models Think Too Fast To Explore Effectively

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-20T03:48:03.308456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bfec7fb4-dc77-4fd0-a9d2-a83f27d432ce · inbound

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes cites this paper.

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes Large Language Models Think Too Fast To Explore Effectively

Reference 184

Resolution: verified exact; arxiv_id, observed 2026-07-03T05:57:41.554124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.