Paper Citation Record · LEDGER

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

As of 18 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2607.26865.

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

pith.paper-citation-record.v1
2607.26865 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-30T18:50:46.434389Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

23 of 23 outbound references displayed

verified exact0
verified fuzzy0
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 01a2fb88-95a7-4b8c-b180-cd43f39b8bd3 · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.180240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85b7ea6-d711-48e9-9e31-9fbbcae958e7 · outbound

This paper cites an unresolved cited work.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.314617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ead96fd-c18f-4718-8565-c6cb6b9fc157 · outbound

This paper cites an unresolved cited work.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.720039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c01c4bb4-2a54-4e3c-afd8-668333d86cae · outbound

This paper cites Uncertainty Estimation in Autoregressive Structured Prediction.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Uncertainty Estimation in Autoregressive Structured Prediction

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.778801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50c863c4-7ce3-482e-b617-20e746eafb18 · outbound

This paper cites RouteLLM: Learning to Route LLMs with Preference Data.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents RouteLLM: Learning to Route LLMs with Preference Data

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.839927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71aff614-c18c-4217-9a01-1a35eb4ed1d4 · outbound

This paper cites ReDAct: Uncertainty-Aware Deferral for LLM Agents.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents ReDAct: Uncertainty-Aware Deferral for LLM Agents

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.897225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e463e5-a980-49d6-8e31-15b3055ea4d1 · outbound

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

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.958553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3488cf4b-9d9d-4c52-a7f4-8bd93fce3857 · outbound

This paper cites EAT: Efficient adaptive thinking for LLMs via early exit.arXiv preprint arXiv:2503.05061,.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents EAT: Efficient adaptive thinking for LLMs via early exit.arXiv preprint arXiv:2503.05061,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.020231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 389dc7f3-29dc-46cf-aa59-77823004f54a · outbound

This paper cites Thought calibration: Efficient and confident test-time scaling.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Thought calibration: Efficient and confident test-time scaling

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.081641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa55fc48-e432-457a-a284-f650aa4352e3 · outbound

This paper cites On-Device Language Models: A Comprehensive Review.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents On-Device Language Models: A Comprehensive Review

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.134011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa18767-100d-4500-9cd4-eaa65344a713 · outbound

This paper cites Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.197482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de4b7e55-dfb8-4707-8895-8bef7a3cd687 · outbound

This paper cites Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.257802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a1c3858-ca5a-4bc2-86bf-1fdeb6aa0062 · outbound

This paper cites Mean Token Entropy (MTE): UMTE(y|x) = 1 L LX i=1 H(τ i |x, τ<i, θ),(11) whereH(τ i | ·)is the Shannon entropy of the token distribution at positioni.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Mean Token Entropy (MTE): UMTE(y|x) = 1 L LX i=1 H(τ i |x, τ<i, θ),(11) whereH(τ i | ·)is the Shannon entropy of the token distribution at positioni

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.354755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09df9440-d0b5-4730-9f4e-dcec6f2d5fe5 · outbound

This paper cites D THOUGHTCALIBRATION: STOPPINGRULEILLUSTRATION Fig.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents D THOUGHTCALIBRATION: STOPPINGRULEILLUSTRATION Fig

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.397622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e00f5c82-e2ea-4ede-ae14-3e6582ea2818 · outbound

This paper cites Therefore I am. I Think.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Therefore I am. I Think

Reference 1961

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.477848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40329375-5c01-4898-b998-637a39e27614 · outbound

This paper cites Conformal prediction for large language model inference.arXiv preprint arXiv:2502.09535,.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Conformal prediction for large language model inference.arXiv preprint arXiv:2502.09535,

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.598650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 900df132-7b18-43b7-bf26-856e4296508f · outbound

This paper cites Program Synthesis with Large Language Models.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Program Synthesis with Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.297998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d107987-670e-45b0-9a04-fde8df978bee · outbound

This paper cites Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.243193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f20a5552-0273-479e-b860-0789c09bf0d1 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Training Verifiers to Solve Math Word Problems

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.418472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1b52e4b-9023-4846-93c1-6cdc36c46044 · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.357626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69932df2-8412-407f-ab84-30511cd02f96 · outbound

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

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.657666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b23815b2-fa9f-4e2f-b844-e0e35c09a802 · outbound

This paper cites Statistically Valid Hyperparameter Selection: From Tuning to Guarantees.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Statistically Valid Hyperparameter Selection: From Tuning to Guarantees

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:45.537551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 826b01ba-9321-4b2c-90fc-f401a9622268 · outbound

This paper cites only-large-right.

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents only-large-right

Reference 3584

Resolution: unresolved; no resolver link, observed 2026-07-30T18:50:46.434389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.