Yang Li
Author directoryHong Kong Metropolitan, Guangdong
Other people with similar names: Yang Li, Yang Li, Yang Li (College of William and Mary), Yang Li, Yang Li, Yang Li, Yang Li, Yang Li, Yang Li, Yang Li, Yang Li (Chinese Academy of Sciences), Yang Li, Yang Li, Yang Li (CMU, Iowa State)
Unverified author pages with similar names: Yang Li
2026
BMAM: Brain-inspired Multi-Agent Memory Framework
Yang Li | Jiaxiang Liu | Yusong Wang | Yujie Wu | Mingkun Xu
Findings of the Association for Computational Linguistics: ACL 2026
Yang Li | Jiaxiang Liu | Yusong Wang | Yujie Wu | Mingkun Xu
Findings of the Association for Computational Linguistics: ACL 2026
Language-model-based agents operating over extended interaction horizons face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions, a failure mode we term “soul erosion.” We present BMAM (Brain-inspired Multi-Agent Memory), a general-purpose memory architecture that models agent memory as a set of functionally specialized subsystems rather than a single unstructured store. Inspired by cognitive memory systems, BMAM decomposes memory into episodic, semantic, salience-aware, and control-oriented components that operate at complementary time scales, organised as a six-phase memory lifecycle. To support long-horizon reasoning, BMAM organises episodic memories along explicit timelines and retrieves evidence by fusing multiple complementary signals. Experiments on the LoCoMo benchmark show that BMAM achieves 78.45% accuracy, outperforming seven memory-augmented baselines. Pairwise ablations reveal super-additive synergy between brain-region components rather than redundant stacking, and a Soul Portability Test demonstrates 87.5% identity-integrity across full memory export, clear, and restore. A targeted refinement of the temporal-trigger heuristics raises LongMemEval multi-session accuracy from 45.2% to 56.4%, validating the architectural decomposition behind BMAM.Code is available at https://github.com/innovation64/BMAM.
AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents
Yang Li | Jiaxiang Liu | Jiang Cai | Mingkun Xu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Yang Li | Jiaxiang Liu | Jiang Cai | Mingkun Xu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
A situated query like "where is Lin Wei?" often encodes more than its literal content: the user may also want to know whether Lin Wei is free, in a good mood, or worth interrupting now. Standard tool-use agents answer the literal question and stop. AURA inserts an inference step between scene perception and tool use that produces an IntentFrame: a structured estimate of the implicit need with a scalar gap score that controls per-query probe budget and tool selection. On a 100-query four-scene implicit-intent benchmark, AURA improves implicit-need coverage over ReAct-style probing (Delta = +0.07, p < 10^-6); three of four scenes are individually significant, the gain reproduces on a second backbone, and a prompt ablation attributes the lift to gap calibration rather than answer memorisation. A component ablation localises the gain further: the gap-derived budget ceiling alone outperforms the full architecture (p = 0.02), and bin-wise calibration analysis (r = -0.33) identifies the gap score as a probe trigger rather than a calibrated value estimator. On factual lookup the controller trades raw accuracy for 82% fewer probes and zero forbidden-tool violations on a privacy-sensitive slice; scope conditions are detailed in Limitations. Code, simulator, and benchmark are released at https://github.com/innovation64/AURA, with the implicit-intent benchmark also on the HuggingFace Hub (innovation64/aura-implicit-intent).
MM-NeuroOnco: A Multimodal Benchmark and Instruction Dataset for MRI-Based Brain Tumor Diagnosis
Feng Guo | Jiaxiang Liu | Yang Li | Qianqian Shi | Mingkun Xu
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Feng Guo | Jiaxiang Liu | Yang Li | Qianqian Shi | Mingkun Xu
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Brain tumor MRI diagnosis requires models not only to identify lesions but also to perform fine-grained medical reasoning based on imaging modality, tumor location, and key imaging findings. However, existing medical multimodal datasets often lack structured diagnostic semantics, and closed-ended evaluations may overestimate model ability due to option cues or elimination shortcuts. To address this issue, we introduce MM-NeuroOnco, a large-scale multimodal instruction dataset and benchmark for brain tumor MRI diagnostic reasoning, containing 24,726 MRI slices from 20 public data sources and approximately 200,000 multimodal instructions grounded in imaging evidence. We develop a multi-model collaborative pipeline for semantic completion and quality control, which supplements original tumor labels and segmentation masks with key diagnostic attributes, and further construct MM-NeuroOnco-Bench with a no-LLM-inference policy for ground-truth labels. The benchmark adds a “None of the above” option to closed-ended questions to reduce evaluation bias caused by option shortcuts. Experiments show that existing general-purpose and medical-specialist multimodal large models remain limited on this task, with the strongest baseline achieving only 41.88% accuracy on diagnosis-related questions. Fine-tuning on MM-NeuroOnco yields NeuroOnco-GPT, achieving a 27% absolute accuracy improvement and demonstrating the effectiveness of our dataset in enhancing fine-grained multimodal medical reasoning. Code and dataset documentation are available at https://github.com/gfnnnb/MM-NeuroOnco.
2025
CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering
Zongxi Li | Yang Li | Haoran Xie | S. Joe Qin
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Zongxi Li | Yang Li | Haoran Xie | S. Joe Qin
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Users often assume that large language models (LLMs) share their cognitive alignment of context and intent, leading them to omit critical information in question-answering (QA) and produce ambiguous queries. Responses based on misaligned assumptions may be perceived as hallucinations. Therefore, identifying possible implicit assumptions is crucial in QA. To address this fundamental challenge, we propose Conditional Ambiguous Question-Answering (CondAmbigQA), a benchmark comprising 2,000 ambiguous queries and condition-aware evaluation metrics. Our study pioneers “conditions” as explicit contextual constraints that resolve ambiguities in QA tasks through retrieval-based annotation, where retrieved Wikipedia fragments help identify possible interpretations for a given query and annotate answers accordingly. Experiments demonstrate that models considering conditions before answering improve answer accuracy by 11.75%, with an additional 7.15% gain when conditions are explicitly provided. These results highlight that apparent hallucinations may stem from inherent query ambiguity rather than model failure, and demonstrate the effectiveness of condition reasoning in QA, providing researchers with tools for rigorous evaluation.
Search