Related papers: RECTOR: Priority-Aware Rule-Based Reranking for Co…

Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. [1] presented the first systematic evaluation comparing vector-based agentic RAG against…

Modern retrieval pipelines increasingly serve downstream consumers like retrieval-augmented generation (RAG) and autonomous agents that need more than a scalar relevance score. A reranker that only tells the caller "how relevant" forces the…

Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving, where agents are required to optimize performance under strict safety requirements. This dual objective creates a fundamental tension, as overly…

Reinforcement Learning with Verifiable Rewards (RLVR), particularly with algorithms like Group Relative Policy Optimization (GRPO), has proven highly effective in enhancing the reasoning capabilities of large language models. However, a…

In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage paradigm, but generic reranking models rely on semantic…

Corner cases are rare or extreme scenarios that drive real-world failures, but they are difficult to curate at scale: web data are noisy, labels are brittle, and edge deployments preclude large retraining. We present ReCCur (Recursive…

LLM-as-a-Judge pipelines have become the de facto evaluator for agent safety, yet existing benchmarks treat their verdicts as ground-truth proxies without checking whether the verdicts depend on the agent's behavior or merely on how the…

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many…

Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and…

Classification of movement trajectories has many applications in transportation and is a key component for large-scale movement trajectory generation and anomaly detection which has key safety applications in the aftermath of a disaster or…

Autonomous-driving research has recently embraced deep Reinforcement Learning (RL) as a promising framework for data-driven decision making, yet a clear picture of how these algorithms are currently employed, benchmarked and evaluated is…

Despite notable results in various fields over the recent years, deep reinforcement learning (DRL) algorithms lack transparency, affecting user trust and hindering their deployment to high-risk tasks. Causal confusion refers to a phenomenon…

Many assignment systems require applicants to rank multi-attribute bundles (e.g., programs combining institution, major, and tuition). We study whether this reporting task is inherently difficult and how reporting interfaces affect accuracy…

Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many important model behaviors require satisfying several qualitative criteria at once.…

We revisit the sequential variants of linear regression with the squared loss, classification problems with hinge loss, and logistic regression, all characterized by unbounded losses in the setup where no assumptions are made on the…

Large language models (LLMs) achieve higher accuracy on challenging reasoning tasks by scaling test-time compute through multiple trajectory sampling. However, standard aggregation methods like majority voting or individual confidence-based…

Proactive task-oriented agents must autonomously anticipate user needs, identify actionable opportunities, and trigger software actions at appropriate moments - fundamentally shifting from reactive systems that await explicit instructions.…

Apart from the high accuracy of machine learning models, what interests many researchers in real-life problems (e.g., fraud detection, credit scoring) is to find hidden patterns in data; particularly when dealing with their challenging…

Complying with traffic rules is challenging for automated vehicles, as numerous rules need to be considered simultaneously. If a planned trajectory violates traffic rules, it is common to replan a new trajectory from scratch. We instead…

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…