9 citations · 15 across the 31 of their papers we have counts for
16 papers · 1 filter
Understanding KV Residency in Production-Scale Agentic LLM Workloads
Mayank Arya, Agrim Bari, Anjaly Parayil +4
Agentic large language model (LLM) applications turn one user request into a sequence of model and tool calls over a growing context. Retaining this context's key-value (KV) state…
FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents
Shantanu Dixit, Anson Bastos, Xuchao Zhang +2
LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation from attention dilution. Exist…
PSD: Pseudo Self-Distillation of Memory Representation Capabilities for LLM Agents
Pirzada Suhail, Menglin Xia, Xuchao Zhang +3
Memory systems are becoming a core component of LLM agents, but constructing and maintaining memory remains expensive because it relies on repeated calls to large proprietary langu…
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…
AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
Sungho Park, Wonjoong Kim, Rongyuan Tan +10
LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure. Although external harnesses…
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…
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…
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…
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…
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…
EvidenT: An Evidence-Preserving Framework for Iterative System-Level Package Repair
Chenyu Zhao, Minghua Ma, Shenglin Zhang +5
Frequent toolchain updates and growing ISA diversity have made system-level software package repair increasingly important. Diagnosing and repairing build failures remains challeng…
Revisiting Transformer Layer Parameterization Through Causal Energy Minimization
Jin Xu, Camille Couturier, Victor Rühle +2
Transformer blocks typically combine multi-head attention (MHA) for token mixing with gated MLPs for token-wise feature transformation, yet many choices in their parameterization r…
WebXSkill: Skill Learning for Autonomous Web Agents
Zhaoyang Wang, Qianhui Wu, Xuchao Zhang +12
Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap in existing skill formulations:…
AutoAdapt: An Automated Domain Adaptation Framework for LLMs
Sidharth Sinha, Anson Bastos, Xuchao Zhang +3
Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily…
Budget-Aware Agentic Routing via Boundary-Guided Training
Caiqi Zhang, Menglin Xia, Xuchao Zhang +5
As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable…
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
Menglin Xia, Xuchao Zhang, Shantanu Dixit +6
Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scalin…