University of Technology Sydney

3 related articles

Subscribe to updates

Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) Nov 2, 2026
Retrieval-augmented generation gets three separately optimized agents: TRIO splits query expansion, retrieval judging and answering
Retrieval-augmented generation (RAG), which fetches external material before a language model answers, often falters on weak retrieval and fabricated content. TRIO splits that pipeline into three agents, for query expansion, for judging whether retrieval is sufficient, and for answering, and lets each improve iteratively under its own reward signal: the expansion agent is rewarded by gains in answer quality, the judge agent is supervised by unanimity-voted sufficiency labels, and the answer agent trains with dynamic matching-based rewards plus curriculum learning. Experiments across multiple benchmark datasets report TRIO as more effective than state-of-the-art approaches, and the code is public.
Retrieval-augmented generation (RAG), which fetches external material before a language model answers, often falters on weak retrieval and fabricated content. TRIO splits that pipeline into three agents, for query expansion, for judging whether retrieval is sufficient, and for answering, and lets each improve iteratively under its own reward signal: the expansion agent is rewarded by gains in answer quality, the judge agent is supervised by unanimity-voted sufficiency labels, and the answer agent trains with dynamic matching-based rewards plus curriculum learning. Experiments across multiple benchmark datasets report TRIO as more effective than state-of-the-art approaches, and the code is public.
University of Wisconsin–Madison Peking University University of Technology Sydney
Yingtao Ren（First author）
Retrieval-Augmented Generation TRIO (Task Refinement with Individual Optimization)
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) Oct 14, 2026
Medication recommendation stops at a drug list: RES-MR writes the diagnostic reasoning first, then prescribes inside each patient's own risk boundary
RES-MR splits medication recommendation into two steps, first generating a checkable diagnostic reasoning chain and then adjusting the prescription to each patient's own risk boundary, reaching a 7.7% higher Jaccard than FLAME on MIMIC-III with lower DDI and RIS.
University of Technology Sydney Qilu University of Technology Shandong Academy of Sciences
C Wang（First author）
Large Language Model Knowledge Graph Grounding Clinical Decision Support Knowledge Distillation Reinforcement Learning
arXiv Oct 8, 2026
DRIVE turns successful-trajectory diversity into an RL objective, improving VLA out-of-domain generalization in simulation and on real robots
The authors analyze how reinforcement learning fine-tuning (RFT) reshapes exploration in vision-language-action (VLA) policies, finding that RFT contracts the overall behavior distribution while making successful trajectories more diverse, easier to elicit, and broader in task-valid solution coverage; they then propose DRIVE, which converts temporally aligned similarity among grouped rollouts under matched task conditions into a success-conditioned intrinsic reward, improving out-of-domain success on LIBERO-Plus, ManiSkill3, and RoboTwin 2.0 and raising average out-of-domain success from 64.1% to 73.3% on a dual-arm AgileX PiPER-X platform.
The authors analyze how reinforcement learning fine-tuning (RFT) reshapes exploration in vision-language-action (VLA) policies, finding that RFT contracts the overall behavior distribution while making successful trajectories more diverse, easier to elicit, and broader in task-valid solution coverage; they then propose DRIVE, which converts temporally aligned similarity among grouped rollouts under matched task conditions into a success-conditioned intrinsic reward, improving out-of-domain success on LIBERO-Plus, ManiSkill3, and RoboTwin 2.0 and raising average out-of-domain success from 64.1% to 73.3% on a dual-arm AgileX PiPER-X platform.
Australian National University Nanjing University Harbin Institute of Technology University of Technology Sydney
Haoru Li（First author）
Diversity-Driven RL Fine-Tuning Vision-Language-Action model Global Alignment Kernel Potential-Based Reward Shaping Proximal Policy Optimization

You’re all caught up

Retrieval-augmented generation gets three separately optimized agents: TRIO splits query expansion, retrieval judging and answering

Medication recommendation stops at a drug list: RES-MR writes the diagnostic reasoning first, then prescribes inside each patient's own risk boundary

DRIVE turns successful-trajectory diversity into an RL objective, improving VLA out-of-domain generalization in simulation and on real robots