Pith. sign in

Paper Citation Record · LEDGER

Training Software Engineering Agents and Verifiers with SWE-Gym

As of 12 July 2026, this Paper Citation Record lists 15 of 15 outbound references and 37 inbound Pith citation observations for arXiv:2412.21139.

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

pith.paper-citation-record.v1
2412.21139 v2

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-11T06:31:22.384518+00:00

measured 37 of 37 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-08T17:51:19.542302Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T06:15:00.866473Z

Reference resolution

15 of 15 outbound references displayed

  • verified exact2
  • verified fuzzy4
  • unresolved0
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch8

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e02fa68a-bea8-412d-ae82-21615863d09c · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Training Software Engineering Agents and Verifiers with SWE-Gym Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-05-18T05:20:40.547823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-12T02:20:41.492703+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:05fe0e062e724c711e73ada654b4e19ed2cefd8ef0376f740206e2de4ee9fb63

Observation 10cdbadf-44f1-48b3-99ff-d128fa2a2d12 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Training Software Engineering Agents and Verifiers with SWE-Gym Training Verifiers to Solve Math Word Problems

Reference 2

Resolution
metadata mismatch
local_arxiv, observed 2026-05-18T05:20:40.552827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:8120c15e63f38373bfec28f9340e0c9770bf6266509a9986f707e948ed6aa4b6

Observation 918674c2-ab0b-41cf-a716-f51f223aa6f0 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Training Software Engineering Agents and Verifiers with SWE-Gym Measuring Mathematical Problem Solving With the MATH Dataset

Reference 3

Resolution
metadata mismatch
local_arxiv, observed 2026-05-18T05:20:40.558398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:0b92cef75fc5e0314d5f7fbcc17ecd13740b5626e01a2be21e15eaf1b8e83906

Observation 97008711-ca9e-4fff-890c-2c8a01e9403a · outbound

This paper cites Qwen2.5-Coder Technical Report.

Training Software Engineering Agents and Verifiers with SWE-Gym Qwen2.5-Coder Technical Report

Reference 4

Resolution
metadata mismatch
local_arxiv, observed 2026-05-18T05:20:40.521374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:92c661c6b2dc2fc58e48398e0352309f9d9b99c8ed80dca48722d837a329b898

Observation edfe605a-9aec-4465-a9bb-75eced7763e6 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Training Software Engineering Agents and Verifiers with SWE-Gym Proximal Policy Optimization Algorithms

Reference 5

Resolution
metadata mismatch
local_arxiv, observed 2026-05-18T05:20:40.527257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:84039d45d1f8c3ad7ebb2dfa771efa2bac92cc2143f35d75650e65fbd09a6887

Observation 1c7efcbc-1311-42a1-8ffe-b7ad4f9815f1 · outbound

This paper cites org/CorpusID:33081038.

Training Software Engineering Agents and Verifiers with SWE-Gym org/CorpusID:33081038

Reference 6

Resolution
verified exact
doi, observed 2026-05-18T05:20:40.517032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:a486b2ed03f19baccbaec59c8e895514165254664a2dfd93c3e2a2baf69f1a87

Observation f6bf2e5d-38d0-49b4-9649-2b8adcd5a197 · outbound

This paper cites OpenHands: An Open Platform for AI Software Developers as Generalist Agents.

Training Software Engineering Agents and Verifiers with SWE-Gym OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Reference 7

Resolution
metadata mismatch
local_arxiv, observed 2026-05-18T05:20:40.511516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-07-11T11:50:26.030339Z digest=sha256:1dd920b3a008e43ca05158c31c5431edd4cba61b4320b9327a4bb2987e3100be

Observation fe2c7e9f-6eeb-4093-b116-adbf38238b95 · outbound

This paper cites Advancing LLM Reasoning Generalists with Preference Trees.

Training Software Engineering Agents and Verifiers with SWE-Gym Advancing LLM Reasoning Generalists with Preference Trees

Reference 9

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T05:20:40.532699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:fcb6bc687812ee1cc44b4aa72befea9a8297604a460b625b41d68bb9270a67a5

Observation bd90440c-43dd-4aff-b08d-b42593ce6944 · outbound

This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.

Training Software Engineering Agents and Verifiers with SWE-Gym Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

Reference 10

Resolution
malformed identifier
doi_truncated, observed 2026-05-18T05:20:40.503236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:b35fe095eee284204f22b89b20eed7d6104536b4aef06dffc7d77e0ebeab5bf6

Observation f0b0febd-18cd-41bb-9ee6-6268daf9c69d · outbound

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

Training Software Engineering Agents and Verifiers with SWE-Gym Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Reference 11

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T05:20:40.538094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:c76beae8242927918a3a8cef632d17ccdccbbc43afc136769067f830bbdc4f74

Observation 1f93854a-573e-45f2-aeb6-3f7526bfb638 · outbound

This paper cites Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents.

Training Software Engineering Agents and Verifiers with SWE-Gym Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.542990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:c3a317efa30afecb2aa30ee6585e6f355c4e96b6d92bb4fc53af4f5137bd7ec7

Observation 541373ee-ac1c-4173-bd0f-16d22b35cb4b · outbound

This paper cites an unresolved cited work.

Training Software Engineering Agents and Verifiers with SWE-Gym Unresolved cited work

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T05:20:40.562196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:9af3a2443ffd50deb42ea1c36ad2a55c4216df0015215aed839d5f3cd425588c

Observation fd2a330b-69d4-4f87-bdc8-dde81352a7ac · outbound

This paper cites an unresolved cited work.

Training Software Engineering Agents and Verifiers with SWE-Gym Unresolved cited work

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T05:20:40.565686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:e77d3bde1f2fa56e47d3c6390049636b00362e298c97de5dc972ac94443943b9

Observation 30763c10-c9d4-41f4-a4a9-2c790270b7c1 · outbound

This paper cites an unresolved cited work.

Training Software Engineering Agents and Verifiers with SWE-Gym Unresolved cited work

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T05:20:40.568814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:d1c300942833c8c97da4a3ca51b42053d324fe7afd987b22c3e98a30002c8b36

Observation 0a40294a-1049-4a40-8efd-c52974261c17 · outbound

This paper cites <judgement>YES</judgement>.

Training Software Engineering Agents and Verifiers with SWE-Gym <judgement>YES</judgement>

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-05-18T05:20:40.572521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T05:20:40.483057Z digest=sha256:ae65813216dbe7216391699c85a7763e8396ec90a334903d93d67d584f220c4c

Pith citing papers

Observation 03b0ea48-672e-48dd-b478-b13fb1c45a6f · inbound

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution cites this paper.

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 43

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-05-15T10:27:56.185943Z digest=sha256:af3931851fff36bdbe577c6e77d1c7042926ba72d94ac67dc7f3e7a6f5342061

Observation 72732042-56b0-493f-aac9-19ee53c572b0 · inbound

From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review cites this paper.

From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 186

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-15T02:57:37.873567Z digest=sha256:94e603ddba76c0535b347065cdd7e2e82dcabe63d2e9dd9ed687c63c40a67042

Observation f57e737c-5290-4600-b237-39ca465afbbb · inbound

SWE-smith: Scaling Data for Software Engineering Agents cites this paper.

SWE-smith: Scaling Data for Software Engineering Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 1

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-15T10:22:06.951531Z digest=sha256:edbef38c11b07fe57da2dd2ecbbbc62039a07bab75274a43957ba535d72984de

Observation 1c0a0eb8-eeb9-489d-beb4-0464fa0eac73 · inbound

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning cites this paper.

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 48

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-13T10:13:58.774968Z digest=sha256:8c582f540271c28f8ab20e884efa222d3478fa5f3d518237bdd48556e752f3b9

Observation c4a86915-22c8-4c5d-9807-11fa6c93d83f · inbound

Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems cites this paper.

Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 44

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-18T02:02:24.259455Z digest=sha256:7be9ed69acd76eb5e9708816202c9ef9b24e28222e898c133d5869ca6bcf2a1b

Observation f7f4dc8c-9c25-4418-8b07-c46f99432efa · inbound

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory cites this paper.

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 216

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-05-14T23:13:15.016486Z digest=sha256:383d0c47156921c0096c1af37ee432a98b9d7374d52248d32d048ce7c0ba884e

Observation 470f13bf-0a8f-47ed-add5-fda8e2ad17b4 · inbound

SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios cites this paper.

SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 37

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-05-16T20:24:40.939455Z digest=sha256:e1e07014816cf57003955e0dc019abd5c7d7ffda4b5f6e9bbab070d255ec60a2

Observation 07364e05-a955-4f0d-8859-63c9138d9cb5 · inbound

Toward Training Superintelligent Software Agents through Self-Play SWE-RL cites this paper.

Toward Training Superintelligent Software Agents through Self-Play SWE-RL Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 36

Resolution
verified exact
local_arxiv, observed 2026-05-21T16:10:20.237605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-21T16:07:48.570995Z digest=sha256:b6ba874e3ff048756d62cd047c865ef6211d679e77f3c68e4d84e872dd7cfbf0

Observation cd065dcb-18ce-4e9e-904b-3407900cc6fc · inbound

Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs cites this paper.

Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 10

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-13T22:33:48.548362Z digest=sha256:01bf424a2188dc035474d072869d6d824686f4c19ca4c7de4e59a2175ea9379c

Observation e8ecfba8-95fe-44d1-8ec5-4c0f6c5d8c86 · inbound

REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage cites this paper.

REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 10

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-13T21:40:08.756892Z digest=sha256:fe33168af2bd52be21c0bba16c26cda60f7e5ee52303a6307af8c88fab603840

Observation d1448aee-9992-4057-b05c-4422b41c4eae · inbound

Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents cites this paper.

Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-15T12:22:13.551709Z digest=sha256:9ac7eb6319209a287d3d2c05883f97b718263cbcd1cc00c4b194cd18476656ec

Observation 0b65129b-ea75-45e4-9029-9727a53dfc4f · inbound

Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering cites this paper.

Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 23

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-10T07:29:03.994957Z digest=sha256:0d536afdaed78c6e4def2c6c76d991561a9970cc6c823abfa2f715a05579f204

Observation a4041e86-9675-4d7a-9c93-04dc5a768f94 · inbound

LLM-Guided Issue Generation from Uncovered Code Segments cites this paper.

LLM-Guided Issue Generation from Uncovered Code Segments Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-07T15:55:53.470494Z digest=sha256:90d5f2164135a3b6986e2100caf5cad5a9b001e0c5b06d2132e1493720bcabe5

Observation 7c61fe38-f34d-4dca-9f38-d175d05711a3 · inbound

LLM-Guided Issue Generation from Uncovered Code Segments cites this paper.

LLM-Guided Issue Generation from Uncovered Code Segments Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-08T03:08:54.186080Z digest=sha256:729abaed62dcc2f067ad0b81616a296647eb968707a9ffca17d00b932544edd4

Observation 2fe1c6ca-1731-45a1-95b2-75c2d124da56 · inbound

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning cites this paper.

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 90

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-05-10T19:15:27.406778Z digest=sha256:7aae3a8c77db258078daf55583a4dc789b627ea3fcf9cf98cc99703ba8b5efcc

Observation 956c625d-c791-4a46-9f9c-1b807f29a419 · inbound

CoT-Guard: Small Models for Strong Monitoring cites this paper.

CoT-Guard: Small Models for Strong Monitoring Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-14T19:39:16.264272Z digest=sha256:220e8c049b811c7c4d88060480c2deb53e9e8d881d455618b18b33e2df897367

Observation 527fa34d-1bb3-4629-b3ef-1c8ec9fccfc7 · inbound

Revisiting DAgger in the Era of LLM-Agents cites this paper.

Revisiting DAgger in the Era of LLM-Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 25

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-14T19:56:06.762156Z digest=sha256:c83ca9dd5f49d3bebf0e94b7f615314c5457ea5e4ae3deec8da817abb0105901

Observation 76f74d80-a947-4d60-8ea2-1f569726f4ba · inbound

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation cites this paper.

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 26

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T05:20:40.573423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-05-14T18:51:06.379266Z digest=sha256:5966ea146b45b3eb8463bfa4c9b39a117b56b429b5360a261c567d816a72da2f

Observation 9180c915-64ed-42e6-9bb5-b6687947e4b2 · inbound

Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench cites this paper.

Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 27

Resolution
metadata mismatch
local_arxiv, observed 2026-05-19T17:52:43.059817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-05-19T17:49:01.198956Z digest=sha256:efb6ea668fc6000f6efef51e31f817587e468e61ecc27e12b16e093057f71e42

Observation 8b38604c-88ab-42d7-aead-e7030d56673b · inbound

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control cites this paper.

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 46

Resolution
verified exact
local_arxiv, observed 2026-05-20T12:28:16.685555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-20T12:26:19.000336Z digest=sha256:6427b35b691014c0de9e5bb3103617f95faa257c858924c0b22d8cd16fd8c4f6

Observation d42a6568-7c57-4397-9f00-37930e562894 · inbound

MemGym: a Long-Horizon Memory Environment for LLM Agents cites this paper.

MemGym: a Long-Horizon Memory Environment for LLM Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 32

Resolution
verified exact
local_arxiv, observed 2026-05-21T04:59:36.369144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-21T04:58:41.043782Z digest=sha256:a061458c76bda3b511e947dfc574c461a7bbd638a50d60a5a949c2b84d416ba7

Observation 8269c58f-5f1b-4969-9b79-d3f9d5c0c89a · inbound

From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents cites this paper.

From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-05-22T05:14:37.568273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-05-22T05:13:26.057531Z digest=sha256:315e33acee8985498fff84de999e8a8b3d7c8fde61a8d1262ccaf69640488721

Observation 3216c98d-2a17-41e0-a9ea-612031e6e5f1 · inbound

Stop Comparing LLM Agents Without Disclosing the Harness cites this paper.

Stop Comparing LLM Agents Without Disclosing the Harness Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 30

Resolution
verified exact
local_arxiv, observed 2026-07-01T13:25:45.855902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-30T23:15:37.160073Z digest=sha256:85c098d997187a9baeda91fc87674aab18a17437a5add8b0e1c85d3211431c17

Observation 11a321a6-c198-475a-a32f-c00e74e7a3cf · inbound

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents cites this paper.

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 13

Resolution
verified exact
local_arxiv, observed 2026-06-29T21:43:59.218366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-29T21:40:36.033696Z digest=sha256:a71b27da5aeb7a3a0d4b4c3e1eb73392d7e0dbbeee8ea89024213b9538374581

Observation 06066990-15a8-4785-a77c-330a1d3dfe4e · inbound

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World cites this paper.

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 22

Resolution
verified exact
local_arxiv, observed 2026-06-29T21:33:58.830178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-29T21:32:41.282694Z digest=sha256:ab928765fbce1b8be10c7a47a2a946a7f7455d2c66560e744c0a4a568e87e273

Observation f490a6e6-4bc6-4117-bc7b-c7a6467dcaaf · inbound

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments cites this paper.

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 56

Resolution
verified exact
local_arxiv, observed 2026-06-29T16:53:40.583201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-29T16:51:36.524194Z digest=sha256:eceb94145dfd1d2e73569f8680127ec7ccae4694ca123e99921cd4cb64da5da4

Observation 0547696b-0739-476c-897e-94cf8d48c7b3 · inbound

unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning cites this paper.

unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 7

Resolution
metadata mismatch
local_arxiv, observed 2026-06-29T11:23:20.896397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-29T11:19:38.959705Z digest=sha256:9b2f4e90fb0dfb3cabc287cdd48ce22098dc364dc4ef2713fe5948c563350546

Observation acd439dc-b729-4903-9f8a-27974eac004f · inbound

Trading Human Curation for Synthetic Augmentation in RLVR cites this paper.

Trading Human Curation for Synthetic Augmentation in RLVR Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 29

Resolution
verified exact
local_arxiv, observed 2026-07-02T02:16:26.236995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-28T11:10:06.685591Z digest=sha256:d4053e1d361eddd8f757c75ad6efcbcd1525b3ca1e7931f9dc865f2386653ad6

Observation f06d3ee0-bba0-4c2e-be62-1b290a1a7164 · inbound

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks? cites this paper.

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks? Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 57

Resolution
verified exact
local_arxiv, observed 2026-07-02T07:46:46.607942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-06-28T06:37:03.670571Z digest=sha256:89ab9f69936a617ccaed6d8fa9bb8a927524d31ae0d7f2b0dd9cc85a38c3f812

Observation 83a494e3-917f-43af-970f-d8b8b9ab59a9 · inbound

AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents cites this paper.

AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 12

Resolution
metadata mismatch
local_arxiv, observed 2026-07-02T11:56:55.500872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-06-28T02:45:25.694378Z digest=sha256:9de140861721fd39663be6dd5b732b47b519a410ac12bd474756fcc4df75c15d

Observation 11110376-e193-4eaf-b719-5bdc5b748cfc · inbound

SWE-Explore: Benchmarking How Coding Agents Explore Repositories cites this paper.

SWE-Explore: Benchmarking How Coding Agents Explore Repositories Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 15

Resolution
verified exact
local_arxiv, observed 2026-07-02T19:47:19.191943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-27T21:21:43.468977Z digest=sha256:58a71b901b7937dc397809366feebe42982ba8d567b1bd0e6df072cbff7a9dfe

Observation ab2ed411-bef1-4930-aaf1-355619881eb2 · inbound

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier cites this paper.

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 27

Resolution
metadata mismatch
local_arxiv, observed 2026-07-03T08:57:48.262807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-06-27T10:36:09.211639Z digest=sha256:d8c96bad117d7db86cf04d0952c3c3f783bc2025d12bffd561792c7550d606f6

Observation 6c92e3a1-9b5e-4936-af74-0021ba44eafe · inbound

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns cites this paper.

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 42

Resolution
verified exact
local_arxiv, observed 2026-07-04T02:19:23.878416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-26T19:47:59.090249Z digest=sha256:ad74e4bf3d4e00746c8afd4e4d8d6b479e9b128b10ac9e9fd278b4ba6cb94b35

Observation 521acd39-b3db-4831-ae71-3abf0414420c · inbound

GRADE: Graph Representation of LLM Agent Dependency and Execution cites this paper.

GRADE: Graph Representation of LLM Agent Dependency and Execution Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 129

Resolution
verified exact
local_arxiv, observed 2026-07-04T09:39:46.465818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=arxiv_source observed=2026-06-26T09:44:37.914985Z digest=sha256:6bc6ed6af3d20796206f65171315f36ee1ad5dafe06d7753fd5c58f0037717ba

Observation deb04e5f-4969-4e0c-a54a-a49b43ca8189 · inbound

How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring cites this paper.

How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 43

Resolution
verified exact
local_arxiv, observed 2026-07-04T14:29:53.444373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-06-26T03:49:43.791435Z digest=sha256:fe15895c468cfdfe023ab3b728d4c3c93d245215e520e9076ed01ef7f0b698c1

Observation 53943bb4-619c-4f22-b6b2-fe763e432685 · inbound

How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring cites this paper.

How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 43

Resolution
verified exact
local_arxiv, observed 2026-07-03T22:49:00.628531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-07-03T22:48:44.389705Z digest=sha256:e12d91fef57e72ff37860f41affb630d18ac30127c7b804430ccbb97511de0db

Observation 6ca114ef-a57b-420a-86f6-1b98ccca4b01 · inbound

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review cites this paper.

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 27

Resolution
verified exact
local_arxiv, observed 2026-07-08T17:55:20.795862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-11T06:31:22.384518+00:00.

source=pdf_text observed=2026-07-08T17:51:19.542302Z digest=sha256:6bb8830c222454c4bed4e00bde8c1d3a0ce32850b9a450a1ec75b7d6a974375d