21 papers
ChronoVision: Temporal Reasoning via Latent State Reconstruction
Yifan Shen, Jian Xu, Boyi Li +6
Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reasoning. This degradation largely stem…
EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +13
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.…
Long-Horizon Embodied Decision-Making via Multimodal Memory Compression
Bingxuan Li, Rui Yang, Cheng Qian +6
Agents are increasingly expected to act not only as task executors, but also as decision-makers on behalf of human users. This shift requires agents to accumulate evidence over lon…
CUADebug: Diagnosing and Repairing Computer-Use Agent Failures
Weijia Zhang, Kunlun Zhu, Zeyi Liu +8
Computer-use agents (CUAs) operate real desktop and web interfaces through screenshots, mouse and keyboard actions, and stateful UI feedback, yet their failures remain difficult to…
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Kunlun Zhu, Xuyan Ye, Zhiguang Han +9
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but pro…
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
Jiayu Liu, Cheng Qian, Zhenhailong Wang +10
Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are progressively disclosed through…