A language agent's execution history can exceed its context window, requiring its memory system to retrieve complete supporting evidence under a hard token budget. Evidence may span multiple execution events, yet conventional retrievers use fixed token windows and fixed-k metrics that reward individual fragments withou...
Yi-Qi Wang, Jin-Qian Ju, Jia-Qi Zhang et al.· 0 citations
The Correlated Promotion Benchmark (CPB), which evaluates whether candidate claims should be admitted to shared memory, shows that policies which deduplicate sources reject many true claims alongside false ones, whereas policies preserving answer coverage admit nearly as many false claims as unrestricted sharing.
Xiao-Yang Li, Yi-Qi Wang, Chen-Cheng Zhu et al.· 1 citation
This survey examines evidence tracing and execution provenance as foundations for process-level accountability in trustworthy LLM agents and introduces a taxonomy covering trace sources, evidence and execution units, provenance relations, tracing granularity and timing, representation forms, and trust functions.
This work proposes a EA foundation model driven by a parallel encoding strategy that facilitates anchor-conditioned message passing and significantly shortens the inference trajectory by leveraging local structural proximity instead of global search.
Yuanning Cui, Zequn Sun, Wei Hu et al.· Proceedings of the Thirty-Fi...· 1 citation
A dense process supervision method based on fact utility estimation, which models the reasoning process as the accumulation of discrete evidence facts, and converts the estimated fact utilities into dense step-level rewards to guide RL training.
Rongzhi Zhu, Xiang-Yu Liu, Yi Liu et al.· 1 citation
ProMem is proposed, a proactive memory extraction framework that separates details, events, and relations, and uses different extraction strategies for each type, and improves memory completeness and QA accuracy, while keeping a good balance between quality and token cost.
The LLM–KGFR collaborative framework, where an LLM works with a structured retriever, the Knowledge Graph Foundation Retriever (KGFR), achieves strong performance while maintaining scalability and generalization, providing a practical solution for KG-augmented reasoning.
Yuanning Cui, Zequn Sun, Wei Hu et al.· IEEE Transactions on Knowled...· 0 citations
AOPD replaces ineffective negative reinforcement with localized divergence minimization in non-positive advantage regions while preserving positive reinforcement learning and maintains higher policy entropy during training and better capability retention during sequential tool-use adaptation.
Nan Jia, Haojin Yang, Xing-Chen Ma et al.· arXiv.org· 18 citations· ⚡5
OaK is presented, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents and shows that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning.
Xiaohui Zhang, Ze-Qun Sun, Cheng Yang et al.· 0 citations
MAP-Graph is introduced, a provenance-aware memory layer that represents agents, sources, memories, claims, and actions in a typed execution graph and supports provenance as an operational control signal, rather than only post-hoc audit metadata, within the evaluated setting.
