Skip to content

Commit ed215ec

Browse files
committed
Add new papers
1 parent c0485be commit ed215ec

15 files changed

Lines changed: 873 additions & 771 deletions

README.md

Lines changed: 780 additions & 749 deletions
Large diffs are not rendered by default.

data/papers_benchmarks.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@
5656

5757
- title: "GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging"
5858
authors: "Ziyi Ni, Huacan Wang, Shuo Zhang, Shuo Lu, Ziyang He, Wang You, Zhenheng Tang, Yuntao Du, Bill Sun, Hongzhang Liu, Sen Hu, Ronghao Chen, Bo Li, Xin Li, Chen Hu, Binxing Jiao, Daxin Jiang, Pin Lyu"
59-
venue: "arxiv 2025"
59+
venue: "arXiv 2025"
6060
links:
6161
paper: "https://arxiv.org/abs/2508.18993"
6262
github: "https://github.com/QuantaAlpha/GitTaskBench"

data/papers_code_executing_game.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@
1616

1717
- title: "PoE-World: Compositional World Modeling with Products of Programmatic Experts"
1818
authors: "Wasu Top Piriyakulkij, Yichao Liang, Hao Tang, Adrian Weller, Marta Kryven, Kevin Ellis"
19-
venue: "arxiv 2025"
19+
venue: "arXiv 2025"
2020
links:
2121
paper: "https://arxiv.org/abs/2505.10819"
2222
github: ""
Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,3 +5,11 @@
55
paper: "https://arxiv.org/abs/2509.16187"
66
github: ""
77
website: ""
8+
9+
- title: "What a diff makes: automating code migration with large language models"
10+
authors: "Katherine A. Rosenfeld, Cliff C. Kerr, Jessica Lundin"
11+
venue: "arXiv 2025"
12+
links:
13+
paper: "https://arxiv.org/abs/2511.00160"
14+
github: ""
15+
website: ""

data/papers_empirical_studies.yaml

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -14,6 +14,22 @@
1414
github: "https://github.com/ResearchOpenRepos/bug_fixing_agent_empirical_study"
1515
website: ""
1616

17+
- title: "Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories"
18+
authors: "Oorja Majgaonkar, Zhiwei Fei, Xiang Li, Federica Sarro, He Ye"
19+
venue: "arXiv 2025"
20+
links:
21+
paper: "https://arxiv.org/abs/2511.00197"
22+
github: ""
23+
website: ""
24+
25+
- title: "A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks"
26+
authors: "Zhuowen Yin, Cuifeng Gao, Chunsong Fan, Wenzhang Yang, Yinxing Xue, Lijun Zhang"
27+
venue: "arXiv 2025"
28+
links:
29+
paper: "https://arxiv.org/abs/2511.00872"
30+
github: ""
31+
website: ""
32+
1733
- title: "Understanding Software Engineering Agents Through the Lens of Traceability: An Empirical Study"
1834
authors: "Ira Ceka, Saurabh Pujar, Shyam Ramji, Luca Buratti, Gail Kaiser, Baishakhi Ray"
1935
venue: "arXiv 2025"

data/papers_environment_building.yaml

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -22,6 +22,14 @@
2222
github: "https://github.com/R2E-Gym/R2E-Gym"
2323
website: "https://r2e-gym.github.io/"
2424

25+
- title: "Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems"
26+
authors: "Chenyu Zhao, Shenglin Zhang, Zeshun Huang, Weilin Jin, Yongqian Sun, Dan Pei, Chaoyun Zhang, Qingwei Lin, Chetan Bansal, Saravan Rajmohan, Minghua Ma"
27+
venue: "arXiv 2025"
28+
links:
29+
paper: "https://arxiv.org/abs/2511.00780"
30+
github: ""
31+
website: ""
32+
2533
- title: "Repo2Run: Automated Building Executable Environment for Code Repository at Scale"
2634
authors: "Ruida Hu, Chao Peng, Xinchen Wang, Junjielong Xu, Cuiyun Gao"
2735
venue: "NeurIPS 2025"

data/papers_issue_reproduction.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
- title: "Issue2Test: Generating Reproducing Test Cases from Issue Reports"
22
authors: "Noor Nashid, Islem Bouzenia, Michael Pradel, Ali Mesbah"
3-
venue: "arxiv 2025"
3+
venue: "arXiv 2025"
44
links:
55
paper: "https://arxiv.org/abs/2503.16320"
66
github: ""

data/papers_issue_resolution.yaml

Lines changed: 14 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@
4040

4141
- title: "ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory"
4242
authors: "Siru Ouyang, Jun Yan, I-Hung Hsu, Yanfei Chen, Ke Jiang, Zifeng Wang, Rujun Han, Long T. Le, Samira Daruki, Xiangru Tang, Vishy Tirumalashetty, George Lee, Mahsan Rofouei, Hangfei Lin, Jiawei Han, Chen-Yu Lee, Tomas Pfister"
43-
venue: "arxiv 2025"
43+
venue: "arXiv 2025"
4444
links:
4545
paper: "https://arxiv.org/abs/2509.25140"
4646
github: ""
@@ -64,15 +64,15 @@
6464

6565
- title: "Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute"
6666
authors: "Yingwei Ma, Yongbin Li, Yihong Dong, Xue Jiang, Rongyu Cao, Jue Chen, Fei Huang, Binhua Li"
67-
venue: "arxiv 2025"
67+
venue: "arXiv 2025"
6868
links:
6969
paper: "https://arxiv.org/abs/2503.23803"
7070
github: "https://github.com/yingweima2022/SWE-Reasoner"
7171
website: ""
7272

7373
- title: "debug-gym: A Text-Based Environment for Interactive Debugging"
7474
authors: "Xingdi Yuan, Morgane M Moss, Charbel El Feghali, Chinmay Singh, Darya Moldavskaya, Drew MacPhee, Lucas Caccia, Matheus Pereira, Minseon Kim, Alessandro Sordoni, Marc-Alexandre Côté"
75-
venue: "arxiv 2025"
75+
venue: "arXiv 2025"
7676
links:
7777
paper: "https://arxiv.org/abs/2503.21557"
7878
github: "https://github.com/microsoft/debug-gym"
@@ -86,6 +86,14 @@
8686
github: "https://github.com/R2E-Gym/R2E-Gym"
8787
website: "https://r2e-gym.github.io/"
8888

89+
- title: "HAFixAgent: History-Aware Automated Program Repair Agent"
90+
authors: "Yu Shi, Hao Li, Bram Adams, Ahmed E. Hassan"
91+
venue: "arXiv 2025"
92+
links:
93+
paper: "https://arxiv.org/abs/2511.01047"
94+
github: ""
95+
website: ""
96+
8997
- title: "SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution"
9098
authors: "Han Li, Yuling Shi, Shaoxin Lin, Xiaodong Gu, Heng Lian, Xin Wang, Yantao Jia, Tao Huang, Qianxiang Wang"
9199
venue: "arXiv 2025"
@@ -168,7 +176,7 @@
168176

169177
- title: "A Self-Improving Coding Agent"
170178
authors: "Maxime Robeyns, Martin Szummer, Laurence Aitchison"
171-
venue: "arxiv 2025"
179+
venue: "arXiv 2025"
172180
links:
173181
paper: "https://arxiv.org/abs/2504.15228"
174182
github: "https://github.com/MaximeRobeyns/self_improving_coding_agent"
@@ -184,7 +192,7 @@
184192

185193
- title: "Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning"
186194
authors: "Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Sergey Abramov, Andrei Andriushchenko, Filipp Fisin, Sergei Skvortsov, Boris Yangel"
187-
venue: "arxiv 2025"
195+
venue: "arXiv 2025"
188196
links:
189197
paper: "https://arxiv.org/abs/2508.03501"
190198
github: ""
@@ -208,7 +216,7 @@
208216

209217
- title: "Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments"
210218
authors: "Hongjin Su, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, Sercan Ö. Arık"
211-
venue: "arxiv 2025"
219+
venue: "arXiv 2025"
212220
links:
213221
paper: "https://arxiv.org/abs/2501.10893"
214222
github: ""

data/papers_machine_learning_engineering.yaml

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -22,6 +22,14 @@
2222
github: ""
2323
website: ""
2424

25+
- title: "PerfDojo: Automated ML Library Generation for Heterogeneous Architectures"
26+
authors: "Andrei Ivanov, Siyuan Shen, Gioele Gottardo, Marcin Chrapek, Afif Boudaoud, Timo Schneider, Luca Benini, Torsten Hoefler"
27+
venue: "arXiv 2025"
28+
links:
29+
paper: "https://arxiv.org/abs/2511.03586"
30+
github: ""
31+
website: ""
32+
2533
- title: "AIDE: AI-Driven Exploration in the Space of Code"
2634
authors: "Zhengyao Jiang, Dominik Schmidt, Dhruv Srikanth, Dixing Xu, Ian Kaplan, Deniss Jacenko, Yuxiang Wu"
2735
venue: "arXiv 2025"

data/papers_multimodal_coding.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@
2424

2525
- title: "GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging"
2626
authors: "Ziyi Ni, Huacan Wang, Shuo Zhang, Shuo Lu, Ziyang He, Wang You, Zhenheng Tang, Yuntao Du, Bill Sun, Hongzhang Liu, Sen Hu, Ronghao Chen, Bo Li, Xin Li, Chen Hu, Binxing Jiao, Daxin Jiang, Pin Lyu"
27-
venue: "arxiv 2025"
27+
venue: "arXiv 2025"
2828
links:
2929
paper: "https://arxiv.org/abs/2508.18993"
3030
github: "https://github.com/QuantaAlpha/GitTaskBench"

0 commit comments

Comments
 (0)