Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 16 of 16 for “"GRPO"”.

  1. POST-TRAINING OF VISION-LANGUAGE AGENTS FOR DECENTRALIZED AUTONOMOUS VEHICLE COORDINATION USING GENERALIZABLE MULTI-AGENT REWARDS

    … extend AR1’s Group Relative Policy Optimization (GRPO) post-training by augmenting thereward with Expectation Alignment (ELIGN), an intrinsic social term that penalizes mismatch between a learned neighbor-expectation model and the realized shared next observation. To make ELIGN applicable to AR1’s …

    maryland Repository record for POST-TRAINING OF VISION-LANGUAGE AGENTS FOR DECENTRALIZED AUTONOMOUS VEHICLE COORDINATION USING GENERALIZABLE MULTI-AGENT REWARDS (opens in a new tab)

  2. Didžiųjų kalbos modelių loginio mąstymo gebėjimų tobulinimas lietuvių kalbai taikant sustiprinimo mokymą: metodologija, duomenų paruošimas ir palyginamoji analizė /

    … was trained using three different algorithms: GRPO, DAPO, and LogicRL Reinforce++. The primary objective of the experiment was to incentivize the model to generate accurate, deep, and coherent reasoning chains to successfully solve complex logical tasks. The experimental results revealed that …

    vilnius Repository record for Didžiųjų kalbos modelių loginio mąstymo gebėjimų tobulinimas lietuvių kalbai taikant sustiprinimo mokymą: metodologija, duomenų paruošimas ir palyginamoji analizė / (opens in a new tab)

  3. Object Segmentation Reasoning

    … Learning via Group Relative Policy Optimization (GRPO) to optimize spatial precision. The thesis concludes with a critical comparison of these methodologies. While the Multi-Module architecture currently offers superior stability and immediate deployment utility, the End-to-End approach …

    gatech Repository record for Object Segmentation Reasoning (opens in a new tab)

  4. NanoMem: Iterative Evidence Synthesis for Temporal-Causal Reasoning in Agent Memory

    … retrieval round. The Synthesizer is trained with GRPO using multi-level rewards covering answer correctness, evidence compactness, output format, and a per-round sufficiency verdict that provides direct process supervision for the stop-or-continue decision. A new diagnostic benchmark, TimeMemEval, …

    chalmers Repository record for NanoMem: Iterative Evidence Synthesis for Temporal-Causal Reasoning in Agent Memory (opens in a new tab)

  5. LEGAL REASONING WITH SEARCH-AUGMENTED REINFORCEMENT LEARNING: A MULTI-TASK FRAMEWORK

    … patterns. Implemented with Qwen 2.5 3B and GRPO optimization on 8 A100 GPUs, the system achieves a 10.5 percentage point improvement over baselines on LegalBench (59.6% vs. 49.7%), 97% jurisdictional compliance, and 0.72 Spearman correlation between model attention and expert fact importance …

    cornell Repository record for LEGAL REASONING WITH SEARCH-AUGMENTED REINFORCEMENT LEARNING: A MULTI-TASK FRAMEWORK (opens in a new tab)

  6. Test-time fine-tuning via diverse rewards: a conditional variational reward model approach on the abstraction and reasoning corpus

    … through Group Relative Policy Optimization (GRPO) during test time. This dynamic fine-tuning process allows the model to adapt “on the fly,” improving its reasoning and abstraction capabilities with minimal examples and computational overhead. Extensive experiments and ablation studies …

    bu Repository record for Test-time fine-tuning via diverse rewards: a conditional variational reward model approach on the abstraction and reasoning corpus (opens in a new tab)

  7. Neurosymbolic ViT-LoMoE : toward interpretable and knowledge-consistent visual recognition

    … pre-training, supervised LoMoE optimization, and GRPO-based reinforcement-learning fine-tuning of the router which is evaluated from scratch on four plant pathology benchmarks covering both controlled and in-field imaging conditions. Across all backbone configurations, ViT-LoMoE consistently …

    brazil-ufrgs Repository record for Neurosymbolic ViT-LoMoE : toward interpretable and knowledge-consistent visual recognition (opens in a new tab)

  8. When process rewards fail : synthetic negatives and specification gaming in PRM-based RL

    … scale. At Phase 2 — Qwen2.5-7B-Instruct, 500 GRPO steps, three seeds, n_test = 500 — pure process rewards lose roughly thirty accuracy points relative to outcome RL while process_correctness approaches 1.0, with length and redundancy inflation. Composing the PRM with other signals prevents …

    texas Repository record for When process rewards fail : synthetic negatives and specification gaming in PRM-based RL (opens in a new tab)

  9. Multi-Layer OTN Simulation and LLM-Driven Root Cause Analysis: From Alarm Propagation to Reinforcement-Optimized Diagnostic Agents

    … adapters and Group Relative Policy Optimization (GRPO) on Qwen 2.5-3B using composite reward functions. A ReAct agent framework wraps the fine-tuned model with five diagnostic tools; a category-based triage layer routes queries to specialist prompts (Fiber, XCON, or Line), narrowing the search …

    waterloo Repository record for Multi-Layer OTN Simulation and LLM-Driven Root Cause Analysis: From Alarm Propagation to Reinforcement-Optimized Diagnostic Agents (opens in a new tab)

  10. Learning dynamics of deep learning -- force analysis of deep neural networks

    … across finetuning methods such as SFT, DPO, and GRPO. We also highlight the critical role of negative gradients. In particular, we identify the "squeezing effect": a counterintuitive phenomenon caused by improperly applied gradient ascent. Representation learning: We explore the dynamics of …

    ubc Repository record for Learning dynamics of deep learning -- force analysis of deep neural networks (opens in a new tab) Download PDF for Learning dynamics of deep learning -- force analysis of deep neural networks (opens in a new tab)

  11. Towards Smarter Trading: An AI Trading Framework Combining Reinforcement Learning and Large Language Model

    … applies Group Relative Policy Optimization (GRPO) directly to a general-purpose instruction-tuned LLM, enabling the model to develop trading competence purely through reward-driven exploration, without curated professional signals. The model ingests multi-source market observations — …

    washington Repository record for Towards Smarter Trading: An AI Trading Framework Combining Reinforcement Learning and Large Language Model (opens in a new tab)

  12. Advancing multi-session personalization in LLMs via direct policy

    … Hierarchical Group Relative Policy Optimization (GRPO) pipeline to overcome the instability and improve the sample efficiency of the indirect supervision method, which is common for retriever-generator Joint Training. In addition, this study addresses the lack of long horizon, multi-session, …

    texas Repository record for Advancing multi-session personalization in LLMs via direct policy (opens in a new tab)

  13. Toward Reliable Supervision for Foundation Models

    … into Group Relative Policy Optimization (GRPO) while preserving verifier authority: verifier rewards drive learning when they are informative, and PRM-based dense supervision is used only when verifier rewards are degenerate. Step scores are converted into future-cumulated token-level …

    maryland Repository record for Toward Reliable Supervision for Foundation Models (opens in a new tab)

  14. GPS-Driven evacuation analysis and trajectory synthesis using Large Language Models

    … and destination-aware prompting. Through GRPO-based reinforcement fine-tuning, the framework achieves over 85% next-step prediction accuracy and generates trajectories that closely match real spatial distributions, providing a scalable and privacy-preserving tool for evacuation planning …

    calgary Repository record for GPS-Driven evacuation analysis and trajectory synthesis using Large Language Models (opens in a new tab)