This paper introduces RREDCoT, a method for approximating optimal reward redistribution in Chain-of-Thought reasoning language models without additional generation.

This paper studies a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers, and develops a data-driven algorithm to learn parameters and op…

The paper introduces ARCA, a novel credit assignment method that measures token salience directly from the adapter's residual hidden state, addressing the degeneracy of standard intrinsic signals when…

The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…

The paper proposes a novel temporal and structural credit assignment framework to efficiently optimize multi-agent LLM systems by decomposing the error signal and using targeted, discrete gradient upd…

The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world…

The paper introduces a novel, transferable learned attack (LT-MIA) that detects a universal 'signature of memorization' in language models, achieving high accuracy across diverse model architectures (…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

The paper evaluates an automated legal triage system (FETCH) that uses follow-up questions, demonstrating that while low-cost LLMs are effective for classification, generating high-quality questions r…

The paper introduces a novel, training-free method to automatically generate fine-grained evaluation rubrics for LLM-as-a-Judge, and further proposes an iterative fine-tuning strategy that significant…

KACE introduces a novel knowledge-adaptive context engineering framework that separates knowledge storage from usage, significantly improving mathematical reasoning accuracy on challenging benchmarks…

The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto l…

The paper introduces the quotient semivalue mechanism to provide fair data attribution that is resistant to contributors manipulating their reported identities by splitting or duplicating data.

The paper introduces ToolFG, a novel tool-integrated MLLM framework that enhances fine-grained image classification by enabling models to autonomously use external tools to gather verifiable visual cu…

The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.

The paper introduces BlueFin, a challenging benchmark for evaluating LLM agents on complex financial spreadsheet tasks, finding that even frontier models perform poorly, scoring less than 50% on avera…

FineVerify introduces a fine-grained self-verification framework that improves agentic search by decomposing complex questions into verifiable sub-questions, leading to significant accuracy gains over…

This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…