Related papers: TRACER: Verifiable Generative Provenance for Multi…
Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on…
Recent deep research systems have improved the ability of large language models to produce long, grounded reports through iterative retrieval and reasoning. However, most text-centered systems rely mainly on textual evidence, while…
When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is often detached from its execution environment due to privacy or…
Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…
Unified multimodal models integrate the reasoning capacity of large language models with both image understanding and generation, showing great promise for advanced multimodal intelligence. However, the community still lacks a rigorous…
Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…
Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets are too small, and most benchmarks conflate heuristics with inference. We present FOL-Traces, the first large-scale dataset…
When applied to open-domain question answering, large language models (LLMs) frequently generate incorrect responses based on made-up facts, which are called $\textit{hallucinations}$. Retrieval augmented generation (RAG) is a promising…
Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…
Multi-hop question answering is a challenging task in which language models must reason over multiple steps to reach the correct answer. With the help of Large Language Models and their reasoning capabilities, existing systems are able to…
Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether this execution structure is represented inside the model is unknown; prior structural…
Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e.g., Wikipedia) which are then provided as additional context to the generator. For open-ended generation tasks (like…
Agent traces carry increasing analytical value in agentic systems and context engineering, yet most prior work treats conversation format as a trivial implementation detail. Modern agent conversations, however, contain deeply structured…
This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using…
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot…
Despite rapid progress in claim verification, we lack a systematic understanding of what reasoning these benchmarks actually exercise. We generate structured reasoning traces for 24K claim-verification examples across 9 datasets using…
Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial.…
Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way…
Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…
Recently developed pretrained models can encode rich world knowledge expressed in multiple modalities, such as text and images. However, the outputs of these models cannot be integrated into algorithms to solve sequential decision-making…