activity
20242026
most citedOdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows

1 citations · 1 across the 21 of their papers we have counts for

collaborators
Showing cs.SEShow all

11 papers · 1 filter

cs.SE2026

Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?

Zijian Luo, Runzhi He, Pengfei Gao +6

Modern software systems rely heavily on third-party dependencies, but upgrading those dependencies remains a costly maintenance activity. Dependency upgrades do not always preserve…

cs.SE2026

LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation

Han Li, Zhemin Fang, Rili Feng +8

Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing ben…

cs.SE2026

Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments

Haomin Qi, Xingliang Wang, Xuanqi Gao +9

Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a…

cs.SE2026

DepRepair: LLM-Based Source-Code Repair for Dependency Breaking Changes

Shenghao Yang, Bo Lu, Yaochen Liu +5

Modern software projects depend on numerous third-party libraries, whose updates often introduce breaking changes. Adapting consumer code to such changes remains labor-intensive an…

cs.SE2026

AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation

Chenyu Zhao, Shenglin Zhang, Wenwei Gu +5

Large language model (LLM) agents are increasingly used for multi-step, stateful tool-use tasks, yet production reliability remains limited. Unlike static software repair, agent re…

cs.SE2026

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

Chenyu Zhao, Shenglin Zhang, Yihang Lin +7

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose t…