Paper Citation Record · LEDGER

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

As of 23 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2502.04350.

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

pith.paper-citation-record.v1
2502.04350 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T12:16:27.466841Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-20T10:54:54.558241Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T10:58:14.271051Z

Reference resolution

35 of 35 outbound references displayed

verified exact2
verified fuzzy7
unresolved25
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation beab5941-1131-4c0c-8ff0-aeb9f11bc4fd · outbound

This paper cites GPT-4 Technical Report.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.355598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c718da56-c1dd-4164-b480-f3497972b0f0 · outbound

This paper cites Permutation and CombinationGiven a set of objects with specific positioning constraints, the task is to determine the correct arrangement of the objects on a shelf.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Permutation and CombinationGiven a set of objects with specific positioning constraints, the task is to determine the correct arrangement of the objects on a shelf

Reference 2

Resolution: malformed identifier; raw_fallback, observed 2026-08-09T12:16:27.845115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 474d6474-10f7-42e0-bbd9-12186deb9f26 · outbound

This paper cites If the string ends with ‘ba’, replace it with ‘ab’.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance If the string ends with ‘ba’, replace it with ‘ab’

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:16:27.853926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5f464379-657a-4407-9602-1df2c30f6526 · outbound

This paper cites Steering Large Language Models between Code Execution and Textual Reasoning.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Steering Large Language Models between Code Execution and Textual Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.374033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 996155ce-2629-4548-a377-bcbfe0093546 · outbound

This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.380681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4325c0cb-830e-4371-ba4b-2f1d1f7e18eb · outbound

This paper cites LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.384439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ed371dc-9710-4c57-8795-6d7cdbb3e410 · outbound

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

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.387373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c77107a5-d934-4763-ab23-c24eb42ad01e · outbound

This paper cites Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.391313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea9c8a5-468f-4d14-a293-14d2f8b9858e · outbound

This paper cites OpenAI o1 System Card.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance OpenAI o1 System Card

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.394231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c34ab3-9d2f-4735-a80b-9fb7c839f913 · outbound

This paper cites Crafting papers on machine learning.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Crafting papers on machine learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.397359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935d7919-e932-4cb9-96d5-24f6a006e639 · outbound

This paper cites Code as Policies: Language Model Programs for Embodied Control.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Code as Policies: Language Model Programs for Embodied Control

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.403907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee15dd9c-3513-4dc2-843d-13087d2c3323 · outbound

This paper cites Language Models of Code are Few-Shot Commonsense Learners.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Language Models of Code are Few-Shot Commonsense Learners

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.407634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc0ea487-4f92-4fed-a3f2-b9352dbff454 · outbound

This paper cites Self-Refine: Iterative Refinement with Self-Feedback.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Self-Refine: Iterative Refinement with Self-Feedback

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.410546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abfd8128-4b1f-41cb-8e96-c216fadefdfb · outbound

This paper cites Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.413766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9b77044-99b1-45fe-9c5d-727777069825 · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.416734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecc7e009-c3d2-48f7-9e5b-d13af9ef5a38 · outbound

This paper cites Large language models still can’t plan (a bench- mark for llms on planning and reasoning about change).

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Large language models still can’t plan (a bench- mark for llms on planning and reasoning about change)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:16:27.899410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f15a2e6-9cb5-4d1b-88f1-a81bb1b4547a · outbound

This paper cites Mixture-of-Agents Enhances Large Language Model Capabilities.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Mixture-of-Agents Enhances Large Language Model Capabilities

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.423193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a962129e-d7b7-417b-888f-ed5607f8bfc5 · outbound

This paper cites Learning to Reason via Program Generation, Emulation, and Search.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Learning to Reason via Program Generation, Emulation, and Search

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:16:27.541499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dd02c213-2598-434c-9662-413704f3c051 · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.429263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac286b4f-45be-4fe4-b23f-76b00f16ac63 · outbound

This paper cites CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.432261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34b56034-24fb-44ba-9c3a-06e8cf664c3e · outbound

This paper cites Re3: Generating longer stories with recursive reprompting and revision.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Re3: Generating longer stories with recursive reprompting and revision

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:16:27.889511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 52588f2b-ad50-4335-b4fe-3dcb1f3cc182 · outbound

This paper cites Can LLMs Reason in the Wild with Programs?.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Can LLMs Reason in the Wild with Programs?

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:16:27.515540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e7f93f0d-3498-41e3-b7d5-2d4e0b4658ce · outbound

This paper cites Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.442688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49cac612-8a2b-49e0-a987-f26a7b92acbb · outbound

This paper cites Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.445998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d0ba911-8191-4bfc-a10d-c463fe9d0f0e · outbound

This paper cites Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.449334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f5e9f4b-9d27-4baa-82c6-9e93cc6ea019 · outbound

This paper cites However, it fails in medium-difficulty questions since it tends to be overconfident and chooses to answer the question via textual reasoning, which sometimes is wrong.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance However, it fails in medium-difficulty questions since it tends to be overconfident and chooses to answer the question via textual reasoning, which sometimes is wrong

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:16:27.881598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 759908fd-cf06-4362-b606-0b9fc3b491bf · outbound

This paper cites Path PlanThis task involves querying LLMs to plan the robot trajectory waypoints based on human task instructions and environments.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Path PlanThis task involves querying LLMs to plan the robot trajectory waypoints based on human task instructions and environments

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:16:27.872817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b8d33e32-7bbc-42f1-b53f-f8fe8a68a3e8 · outbound

This paper cites MATH-GeometryThis is the math reasoning dataset from MATH dataset (Hendrycks et al., 2021), with specific focus on geometry questions.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance MATH-GeometryThis is the math reasoning dataset from MATH dataset (Hendrycks et al., 2021), with specific focus on geometry questions

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:16:27.863737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9dba4ce4-aea9-4ce0-8874-6798126fbecb · outbound

This paper cites Checker Checker Checker Checker Ave.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Checker Checker Checker Checker Ave

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:16:27.834602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 54962f51-9723-4a76-bf16-26f54468de34 · outbound

This paper cites Chain of Code: Reasoning with a Language Model-Augmented Code Emulator.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.400807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb078dfc-7590-46e5-ab19-dbb46489ae8b · outbound

This paper cites The Llama 3 Herd of Models.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance The Llama 3 Herd of Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.377880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cbeda40-3f8b-4d44-b018-f99e3a380312 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.371006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 117aea19-4896-4035-ad31-92e30be3ff51 · outbound

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

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.359434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11589202-77c9-4a07-8f06-8fc31b7751af · outbound

This paper cites Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.367859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07bf2d63-80c1-401f-9355-dcc7bee372f9 · outbound

This paper cites URL http: //dx.doi.org/10.1145/3690624.3709196.

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance URL http: //dx.doi.org/10.1145/3690624.3709196

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-09T12:16:27.363922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5f9916de-7c19-4ba1-8705-1b7a8f6b801e · inbound

Code as Agent Harness cites this paper.

Code as Agent Harness CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:58:14.273239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.