20 papers
PluginEval: A Diagnostic Benchmark for Fine-Grained Error Attribution in Function Calling
Dongjie Xu, Julius, Hanchi Dong +6
Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents. Current benchmarks face three structural limitations: data distr…
RippleKV: Cross-Layer KV Cache Allocation via Perturbation Propagation
Dongjie Xu, Kai Qian, Julius +6
Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging. Existing methods rely on proxies such as l…
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
Yanping Chen, Weijie Shi, Wen Yang +1
Skill usage can significantly enhance the ability of modern agent systems to complete complex tasks. However, the growing scale of skill libraries makes accurate skill selection in…
SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
Jiawei Li, Ziyi Liu, Weijie Shi +3
3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning…
RL: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
Weijie Shi, Yanxi Chen, Zexi Li +5
Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers…
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
Weijie Shi, Qiang Xu, Fan Deng +9
Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with oppo…