Related papers: CaRT: Teaching LLM Agents to Know When They Know E…

Large Language Models (LLMs) have shown impressive performance in complex reasoning tasks through the use of Chain-of-Thought (CoT) reasoning, allowing models to break down problems into manageable sub-tasks. However, existing CoT…

Retrieval-Augmented Generation (RAG) grounds large language models (LLMs) in external evidence, but fails when retrieved sources conflict or contain outdated or subjective information. Prior work address these issues independently but lack…

The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit…

In this work, we explicitly show that modern LLMs tend to generate correct facts first, then "drift away" and generate incorrect facts later: this was occasionally observed but never properly measured. We develop a semantic drift score that…

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

LLM agents are deployed in environments where they must interact to acquire information. In these scenarios, the agent must reason about inherent cost-uncertainty tradeoffs in how to act, such as when to stop exploring and commit to an…

Learning to communicate in order to share state information is an active problem in the area of multi-agent reinforcement learning (MARL). The credit assignment problem, the non-stationarity of the communication environment and the creation…

Chain-of-thought (CoT) prompting is a popular in-context learning (ICL) approach for large language models (LLMs), especially when tackling complex reasoning tasks. Traditional ICL approaches construct prompts using examples that contain…

Reinforcement Learning (RL) has emerged as a crucial method for training or fine-tuning large language models (LLMs), enabling adaptive, task-specific optimizations through interactive feedback. Multi-Agent Reinforcement Learning (MARL), in…

When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For…

Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such…

Chain-of-Thought (CoT) reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps. However, excessive or redundant reasoning -- so-called overthinking -- can increase…

Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users' contextual search intent when…

Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents.…

Deep Reinforcement Learning (RL) has demonstrated impressive results in solving complex robotic tasks such as quadruped locomotion. Yet, current solvers fail to produce efficient policies respecting hard constraints. In this work, we…

Decision Transformers (DT) play a crucial role in modern reinforcement learning, leveraging offline datasets to achieve impressive results across various domains. However, DT requires high-quality, comprehensive data to perform optimally.…

Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems,…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

Tasks requiring deductive reasoning, especially those involving multiple steps, often demand adaptive strategies such as intermediate generation of rationales or programs, as no single approach is universally optimal. While Language Models…

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…