Related papers: AdaRubric: Task-Adaptive Rubrics for Reliable LLM …

Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense…

Traditional ranking systems optimize offline proxy objectives that rely on oversimplified assumptions about user behavior, often neglecting factors such as position bias and item diversity. Consequently, these models fail to improve true…

Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance…

Hyperparameters are a critical factor in reliably training well-performing reinforcement learning (RL) agents. Unfortunately, developing and evaluating automated approaches for tuning such hyperparameters is both costly and time-consuming.…

Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoRA assumes a uniform…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous…

Collaborative edge computing uses edge nodes in different locations to execute tasks, necessitating dynamic task offloading decisions to maintain low latency and high reliability, especially under unpredictable node failures. Although deep…

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…

While recent Large Vision-Language Models (LVLMs) exhibit strong multimodal reasoning abilities, they often produce ungrounded or hallucinated responses because they rely too heavily on linguistic priors instead of visual evidence. This…

Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm. Meanwhile, despite the rapid advancement of Search…

Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon completion does the dialogue resume. This forces users into a…

Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures of robustness and generalization. This paper attributes these deficiencies to spurious reasoning, i.e.,…

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without…

This paper introduces an adaptive model-free deep reinforcement approach that can recognize and adapt to the diurnal patterns in the ride-sharing environment with car-pooling. Deep Reinforcement Learning (RL) suffers from catastrophic…

A large-scale recommender system usually consists of recall and ranking modules. The goal of ranking modules (aka rankers) is to elaborately discriminate users' preference on item candidates proposed by recall modules. With the success of…

Deep Reinforcement Learning (RL) is well known for being highly sensitive to hyperparameters, requiring practitioners substantial efforts to optimize them for the problem at hand. This also limits the applicability of RL in real-world…

Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current…

AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark enables fair comparison across these approaches. We present Agentick, a…

Distributed trajectory optimization via ADMM-DDP is a powerful approach for coordinating multi-agent systems, but it requires extensive tuning of tightly coupled hyperparameters that jointly govern local task performance and global…