Related papers: SQL-ASTRA: Alleviating Sparse Feedback in Agentic …

Cooperative multi-agent reinforcement learning (MARL) aims to coordinate multiple agents to achieve a common goal. A key challenge in MARL is credit assignment, which involves assessing each agent's contribution to the shared reward. Given…

Multi-turn tool calling is challenging for Large Language Models (LLMs) because rewards are sparse and exploration is expensive. A common recipe, SFT followed by GRPO, can stall when within-group reward variation is low (e.g., more rollouts…

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward Density} in deep search scenarios, where agents expend…

We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that can be applied to most Agent frameworks to support reliable executions (avoiding…

Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than…

Click-through rate (CTR) prediction is a vital task in industrial recommendation systems. Most existing methods focus on the network architecture design of the CTR model for better accuracy and suffer from the data sparsity problem.…

In many real-world applications, it is hard to provide a reward signal in each step of a Reinforcement Learning (RL) process and more natural to give feedback when an episode ends. To this end, we study the recently proposed model of RL…

Text-based games are a popular testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains…

Reinforcement learning (RL) post-training has enabled newer capabilities in models, such as agentic tool-use for search. However, these models struggle primarily due to limitations with sparse outcome-based rewards and a lack of training…

Large-scale Text-to-SQL benchmarks such as BIRD typically assume complete and accurate database annotations as well as readily available external knowledge, which fails to reflect common industrial settings where annotations are missing,…

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…

Click-through rate (CTR) prediction plays an indispensable role in online platforms. Numerous models have been proposed to capture users' shifting preferences by leveraging user behavior sequences. However, these historical sequences often…

Recently, connectionist temporal classification (CTC)-based end-to-end (E2E) automatic speech recognition (ASR) models have achieved impressive results, especially with the development of self-supervised learning. However, E2E ASR models…

Long-term temporal credit assignment is an important challenge in deep reinforcement learning (RL). It refers to the ability of the agent to attribute actions to consequences that may occur after a long time interval. Existing…

As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical methods struggle with pattern shifts, data sparsity, and…

Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several…

Agentic reasoning enables large reasoning models (LRMs) to dynamically acquire external knowledge, but yet optimizing the retrieval process remains challenging due to the lack of dense, principled reward signals. In this paper, we introduce…

Tool use enables large language models to solve complex tasks through sequences of API calls, yet existing reinforcement learning approaches fail to scale to multi-step composition settings. Outcome-based rewards provide only sparse…

Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running…

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…