2 citations · 2 across the 13 of their papers we have counts for
13 papers
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Guibin Zhang, Leo Lu, Fangzhou Xie +15
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can domi…
SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents
Yanze Wang, Pengfei Yao, Tianyi Sun +7
Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them i…
DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
ZhiYan Hou, Xinyu Tang, Hongyan An +9
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals…
CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models
Yu Chen, Xiaohong Li, Xiaole Wang +3
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply.…
HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution
Xiaotian Luo, Dizhan Xue, Fengxingyu Wang +2
Large Language Models (LLMs) have enabled capable agents across diverse applications. Beyond the foundation model, the performance of an agent is governed by the surrounding agent…
EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer
Xingze Gao, Chuanrui Hu, Hongda Chen +9
Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and ve…
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
Yu Chen, Runkai Chen, Sheng Yi +9
Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in the field. Due to the constraints of f…
HyperMem: Hypergraph Memory for Long-Term Conversations
Juwei Yue, Chuanrui Hu, Jiawei Sheng +5
Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, exi…
Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
Chuanrui Hu, Tong Li, Xingze Gao +8
Long-term conversational memory in practical LLM applications is inherently collaborative: information is produced by multiple participants, scattered across groups and channels, r…
MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation
Guoyi Li, Shihao Xu, Jiatong Ma +4
Psychiatric consultation requires agents to elicit discriminative evidence, map uncertain narratives to diagnostic criteria, and decide when evidence suffices. Existing dialogue an…
LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis
Shihao Xu, Tiancheng Zhou, Jiatong Ma +8
Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely…
Beyond the Needle's Illusion: Decoupled Evaluation of Evidence Access and Use under Semantic Interference at 326M-Token Scale
Tianwei Lin, Zuyi Zhou, Xinda Zhao +6
Long-context LLM agents must access the right evidence from large environments and use it faithfully. However, the popular Needle-in-a-Haystack (NIAH) evaluation mostly measures be…
EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
Chuanrui Hu, Xingze Gao, Zuyi Zhou +8
Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extend…