Copertina

From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lindenbauer, Tobias, Groh, Georg, Schütze, Hinrich
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On Git
di: Lindenbauer, Tobias, et al.
Pubblicazione: (2025)

The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
di: Lindenbauer, Tobias, et al.
Pubblicazione: (2025)

Structurally Aligned Subtask-Level Memory for Software Engineering Agents
di: Shen, Kangning, et al.
Pubblicazione: (2026)

Unified Software Engineering Agent as AI Software Engineer
di: Applis, Leonhard, et al.
Pubblicazione: (2025)

From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
di: Ma, Murong, et al.
Pubblicazione: (2026)

AutoCodeRover: Autonomous Program Improvement
di: Zhang, Yuntong, et al.
Pubblicazione: (2024)

Rover: Context-aware Conflict Resolution with LLM
di: Zhang, Qingyu, et al.
Pubblicazione: (2026)

SpecRover: Code Intent Extraction via LLMs
di: Ruan, Haifeng, et al.
Pubblicazione: (2024)

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
di: Trae Research Team, et al.
Pubblicazione: (2025)

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
di: Phan, Huy Nhat, et al.
Pubblicazione: (2024)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
di: Chen, Zhi, et al.
Pubblicazione: (2026)

TOM-SWE: User Mental Modeling For Software Engineering Agents
di: Zhou, Xuhui, et al.
Pubblicazione: (2025)

CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories
di: Chukkapalli, Divya, et al.
Pubblicazione: (2026)

Knowledge Lever Risk Management for Software Engineering: A Stochastic Framework for Mitigating Knowledge Loss
di: Chua, Mark, et al.
Pubblicazione: (2026)

AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering
di: Kumar, Rajesh, et al.
Pubblicazione: (2026)

ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework
di: Tawosi, Vali, et al.
Pubblicazione: (2025)

daVinci-Dev: Agent-native Mid-training for Software Engineering
di: Zeng, Ji, et al.
Pubblicazione: (2026)

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
di: Liang, Jiarong, et al.
Pubblicazione: (2026)

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
di: Gong, Jingzhi, et al.
Pubblicazione: (2026)

Large Language Model-Based Agents for Software Engineering: A Survey
di: Liu, Junwei, et al.
Pubblicazione: (2024)

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
di: Guo, Chuanzhe, et al.
Pubblicazione: (2026)

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents
di: Zhao, Chenyu, et al.
Pubblicazione: (2026)

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
di: Qiu, Jielin, et al.
Pubblicazione: (2025)

Software Reuse in the Generative AI Era: From Cargo Cult Towards AI Native Software Engineering
di: Mikkonen, Tommi, et al.
Pubblicazione: (2025)

Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories
di: Bouzenia, Islem, et al.
Pubblicazione: (2025)

Software Engineering Agents for Embodied Controller Generation : A Study in Minigrid Environments
di: Boulet, Timothé, et al.
Pubblicazione: (2025)

Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap
di: Treude, Christoph
Pubblicazione: (2026)

Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering
di: Benkovich, Nikita, et al.
Pubblicazione: (2026)

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
di: Zhong, Hailin, et al.
Pubblicazione: (2026)

Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents
di: Tse-Hsun, et al.
Pubblicazione: (2026)

The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents
di: Kim, Yelin
Pubblicazione: (2026)

Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults
di: Zhou, Zhenhao, et al.
Pubblicazione: (2025)

MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration
di: Li, Ruiyin, et al.
Pubblicazione: (2025)

LLMs: A Game-Changer for Software Engineers?
di: Haque, Md Asraful
Pubblicazione: (2024)

Software Performance Engineering for Foundation Model-Powered Software
di: Zhang, Haoxiang, et al.
Pubblicazione: (2024)

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory
di: Li, Ruiyin, et al.
Pubblicazione: (2026)

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
di: Ma, Yingwei, et al.
Pubblicazione: (2025)

Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents
di: Ma, Wei, et al.
Pubblicazione: (2026)

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
di: Han, Tingxu, et al.
Pubblicazione: (2026)

Agents in Software Engineering: Survey, Landscape, and Vision
di: Wang, Yanlin, et al.
Pubblicazione: (2024)