LLM-based agents increasingly collaborate with users on long-horizon tasks, accumulating evidence, code, and drafts through extensive search, reasoning, and execution. As users inspect these results, they may supply missing information requirement completion, introduce new requirements requirement elicitation, or revis...
Zhi-Bang Yang, Xin-Ke Jiang, Yuxuan Liu et al.· 0 citations
The cross-signal NTK is introduced, a token-level statistic that measures the alignment between reward and distillation gradients at position n and an empirical threshold beyond which naive mixing can lead to persistent training collapse is revealed.
Xin-Ke Jiang, Tao Feng, Zhi-Bang Yang et al.· 0 citations
GenMem is presented, which reformulates memory management as generative symbolic addressing, a multi-level discrete token tuple drawn from a Cartesian-product address space that factorizes a million-scale sparse memory space using fewer than one hundred discrete symbols.
Xin-Ke Jiang, Tao Feng, Wei-Xuan Xu et al.· 0 citations
LoongReflect is proposed, a training framework that formulates reflection as a memory-control policy over a reversible trajectory tree using explicit reflect and backtrack actions and demonstrates consistent improvements over outcome-only reinforcement learning and self-distillation baselines.
Zhi-Xin Zhang, Xin-Ke Jiang, Zhi-Bang Yang et al.· 0 citations
This work proposes NarraLite, an efficient multimodal generative recommendation framework that jointly compresses perception and reasoning, and establishes a user-agnostic multimodal benchmark for short-form drama continuation across UGC, PGC, and OOD settings.
Chenxing Wang, Nan-Tao Zheng, Hao Miao et al.· 0 citations
Harness-RL is introduced, a structured reinforcement learning framework that combines Conflict-Aware Policy Optimization (CAPO) with interface-level black-box trajectory construction and supports both central-only and joint multi-agent training.
Xin-Ke Jiang, Zhi-Xin Zhang, Zhi-Bang Yang et al.· 1 citation
ScaffoldAgent is proposed, a utility-guided dynamic outline optimization framework for OEDR that models outline evolution as a structured decision process with three operations: Expansion, Contraction, and Revision, enabling controlled updates to the report scaffold.
This work proposes AgenticRag-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning.
Xin-Ke Jiang, Yue Fang, Zhi-Bang Yang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
