arXiv:2606. 00103v1 Announce Type: new Abstract: We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating.
arXiv:2603.18614v2 Announce Type: replace Abstract: Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound...
arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.
arXiv:2608. 12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals.
arXiv:2609.38409v1 Announce Type: new Abstract: Recent progress in large language model reasoning has been driven by benchmarks and reinforcement learning environments with automatically verifiable r...
PROOF is a benchmark that profiles the reliability of object-level facts in instruction-tuned language models by converting a frozen Wikidata snapshot into 18,486 English multiple-choice questions grounded in 11,779 semantic facts across 101 classes, 392 properties, and 14 domains. Each question includes an explicit "I don't know" option, a "No correct option" control, and nine controlled formulations, with 1,849 questions designed as no-correct-option traps. The study evaluates 18 open-weight model deployments on 166,374 prompts, revealing wide variability in factual accuracy, sensitivity to wording changes, and the impact of decoder perturbations.
The paper introduces a text-based, multi-agent version of the board game Clue to test multi-step deductive reasoning in large language models (LLMs). Six LLM-based agents (GPT‑4o‑mini and Gemini‑2.5‑Flash) play turn‑based games, and a tool‑augmented approach uses a structured possibility matrix to convert implicit game state into explicit remaining possibilities, thereby offloading memory and deductive constraints from the agents. The study compares this tool‑augmented method against a baseline to assess its impact on reasoning quality and task success in a strategic reasoning environment.
arXiv:2604. 01161v2 Announce Type: replace Abstract: Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks.
InteractBench is a new benchmark that evaluates large language models on interactive competitive programming problems, where key information is revealed only through queries to an interactor. It contains 322 curated problems from Codeforces, AtCoder, IOI, and ICPC, each with executable local interactors for offline testing. The study finds that even top reasoning models struggle with these tasks, highlighting gaps in information acquisition, state tracking, and protocol adherence.
arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.
The paper surveys efficient reasoning in large language models, contrasting fast intuitive (System 1) and slow deep (System 2) reasoning. It analyzes why System 2 is computationally costly yet more accurate, and why System 1 is efficient but less effective. The survey covers causes of inefficiency, patterns of reasoning behavior, and potential solutions to balance performance and computational budgets, offering actionable insights and an open‑source repository for ongoing research.
The paper introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.
arXiv:2603. 02112v2 Announce Type: replace Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning.