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

This paper explores using Knowledge Components (KCs) as interpretable signals to understand assignment difficulty and student struggle in intro programming courses.

The paper identifies a fundamental mismatch between standard pairwise ranking metrics (like AP and FPR-95) and the true assignment objective in multi-view object association, proposing a Sinkhorn-base…

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…

A new stochastic load balancing model is introduced that allows for a tradeoff between non-adaptive policies and performance, with results showing a 2-reservation approximation to the omniscient optim…

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 the Task Alignment Benchmark (TAB) to evaluate terminal agents' ability to selectively follow relevant environmental instructions while ignoring misleading distractors, revealing…

This paper introduces online assignment policies for stochastic matching on hypergraphs, which are maximally stable and allow for the derivation of necessary and sufficient stability criteria.

This paper studies set-defined graph classes and proves that bounded unions of shift-colorable graphs form the fundamental obstruction to chromatic number boundness in these classes.

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

A new polynomial-time algorithm is presented for optimally coloring perfect graphs using graph-theoretic operations and iterative walk counting.

This paper measures the lower bound for the shortest program generating a sequence, proving a conservation law and providing a deterministic engine to recover generating programs for certain sequences…

This paper identifies a tractability island inside the contextual-fraction problem by collapsing it to a fixed-point calculation for a specific class of permutation-transport models.

This paper introduces a new way to represent finite posets as subwords of finite words in categories, and characterizes the monic categories that admit this representation.

The paper introduces a robust four-stage NLP framework that uses schema-constrained LLMs and ESCO vocabulary to accurately extract and align educational competencies with labor market demands, quantif…

The paper proves equivalence between big-step and small-step derivations for Horn clauses and transforms Horn clauses into equivalent sets of clauses based on the given derivation strategy.

The paper shows that the envy-free cake-cutting problem with three agents is intractable and establishes the first lower bounds for the Jordan curve problem.

The paper addresses limitations in the Linear Ordering Problem (LOP) by introducing a novel benchmark suite derived from current economic data and an algorithmic scheme to generate diverse, high-quali…

This paper documents and analyzes the failure process of strategies used to address conceptual drift in long-horizon LLM collaboration and introduces the concept of 'Index Sickness' and the 'Pang Prin…