Related papers: Detection Without Correction: A Two-Parameter Deco…

The rapid adoption of Large Language Models (LLMs) in interactive systems has enabled the creation of dynamic, open-ended Role-Playing Agents (RPAs). However, evaluating these agents remains a significant challenge, as standard NLP metrics…

Despite the remarkable capabilities of large language models (LLMs) in various reasoning tasks, they still struggle with table reasoning tasks, particularly in maintaining consistency throughout multi-step reasoning processes. While…

Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules…

Can linearly decodable failure signals in LLM hidden states be leveraged to correct those failures? We investigate this classification-correction gap via Overthinking (OT)--a stable behavioral regime (Jaccard >= 0.81, 94% inter-annotator…

Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains inconsistent across models. We recast self-correction as a closed-loop feedback-control…

The evaluation of large language models (LLMs) has predominantly relied on static datasets, which offer limited scalability and fail to capture the evolving reasoning capabilities of recent models. To overcome these limitations, we propose…

Reliable detection of deceptive behavior in Large Language Model (LLM) agents is an essential prerequisite for safe deployment in high-stakes agentic contexts. Prior work on scheming detection has focused exclusively on black-box monitors…

Language Model (LM) pipelines can dynamically refine their outputs against programmatic constraints. However, their effectiveness collapses when faced with competing soft constraints, leading to inefficient backtracking loops where…

Efficient routing across multiple LLMs enables cost-quality tradeoffs by directing queries to the cheapest capable model. Prior work attributes routing headroom to an "unsolvability ceiling", queries no model in the pool can solve. We…

One of the most challenging forms of misinformation involves pairing images with misleading text to create false narratives. Existing AI-driven detection systems often require domain-specific finetuning, limiting generalizability, and offer…

In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand…

Agentic language models compose multi step reasoning chains, yet intermediate steps can be corrupted by inconsistent context, retrieval errors, or adversarial inputs, which makes post hoc evaluation too late because errors propagate before…

Multi-agent debate improves LLM reasoning, yet agreement among agents is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus-based stopping commits that error to an automated action…

When are multi-agent LLM systems merely a collection of individual agents versus an integrated collective with higher-order structure? We introduce an information-theoretic framework to test -- in a purely data-driven way -- whether…

Large-scale decentralized systems of autonomous agents interacting via asynchronous communication often experience the following self-healing dilemma: fault detection inherits network uncertainties making a remote faulty process…

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…

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe…

Large Language Models (LLMs) frequently produce factually inaccurate outputs - a phenomenon known as hallucination - which limits their accuracy in knowledge-intensive NLP tasks. Retrieval-augmented generation and agentic frameworks such as…

Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find…

Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate this skill in fragmented settings, failing to ensure context consistency or cover the full…