Related papers: CARPO: Leveraging Listwise Learning-to-Rank for Co…

Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However,…

Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment methods either optimize on all available tokens, which can be…

The performance of a cross-sectional currency strategy depends crucially on accurately ranking instruments prior to portfolio construction. While this ranking step is traditionally performed using heuristics, or by sorting the outputs…

Enhancing LLMs with the ability to actively search external knowledge is crucial for complex and real-world tasks. Current approaches either rely on prompting to elicit the model's innate agent capabilities, or suffer from performance…

Deciding which large language model (LLM) to use is a complex challenge. Pairwise ranking has emerged as a new method for evaluating human preferences for LLMs. This approach entails humans evaluating pairs of model outputs based on a…

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands…

Continual learning (CL) requires models to continuously adapt to new tasks without forgetting past knowledge. In this work, we propose \underline{P}roactive \underline{L}ow-rank \underline{A}llocatio\underline{N} (PLAN), a framework that…

Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or entire response sequences. However, such formulations often misalign with the natural…

Conversational recommender systems (CRSs) operate under incremental preference revelation, requiring systems to make recommendation decisions under uncertainty. While recent approaches particularly those built on large language models…

Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However, we find that reinforcement learning (RL)-based fine-tuned…

Optimization modeling and solving are fundamental to the application of Operations Research (OR) in real-world decision making, yet the process of translating natural language problem descriptions into formal models and solver code remains…

Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typically treat it as a discrete filter or post-hoc regulator rather…

Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on…

Long-horizon combinatorial optimization problems (COPs), such as the Flexible Job-Shop Scheduling Problem (FJSP), often involve complex, interdependent decisions over extended time frames, posing significant challenges for existing solvers.…

Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we reveal that under practical sampling budgets, Monte Carlo…

Semantic operators abstract large language model (LLM) calls in SQL clauses. It is gaining traction as an easy method to analyze semi-structured, unstructured, and multimodal datasets. While a plethora of recent works optimize various…

Tabular data contains rich structural semantics and plays a crucial role in organizing and manipulating information. Recent methods employ Multi-modal Large Language Models (MLLMs) to address table-related tasks across various modalities of…

Evaluating query predicates on data samples is the only way to estimate their selectivity in certain scenarios. Finding a guaranteed optimal query plan is not a reasonable optimization goal in those cases as it might require an infinite…

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxiliary models or…

Enterprise AI systems increasingly deploy multiple intelligent agents across mission-critical workflows that must satisfy hard policy constraints, bounded risk exposure, and comprehensive auditability (SOX, HIPAA, GDPR). Existing…