RECAST is a reconstruction-based framework that generates chain-of-thought (CoT) explanations from closed‑source reasoning models that only expose final answers, such as Claude‑Sonnet‑5.5, GPT‑6.1, and Gemini 3. Unlike prior extraction methods that rely on visible reasoning fields or scratchpads, RECAST conditions a decoder on the question and the model’s final answer to produce a first‑person structured rationale, cleans it, and outputs data ready for supervised fine‑tuning. The system is open‑source, packaged as an agent skill, and demonstrates successful qualitative reconstructions on the mentioned models using an answer‑only protocol.
arXiv:2608. 20055v1 Announce Type: cross Abstract: Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets.
arXiv:2606. 14935v1 Announce Type: new Abstract: Frontier reasoning-tuned language models still fail on deductive tasks at depth, and the cost of improved performance through extended internal reasoning scales poorly.
TAC-CoT is a framework that replaces explicit chain-of-thought reasoning with compact latent reasoning segments, keeping only textual tokens for tool calls, observations, and final answers. This interleaved design allows large language model agents to use tools without generating full verbal reasoning steps. Experiments on math and QA benchmarks show up to 8.8‑point accuracy gains and a 6.8× reduction in model forward passes, while also improving tool‑use quality in single- and multi‑tool settings.
The paper demonstrates that frontier language models can be prompted to expose their internal chain-of-thought reasoning via a simple custom tool. By comparing these extracted traces to native reasoning on open-source models, the authors confirm that the externalized reasoning aligns with genuine reasoning and outperforms no-reasoning baselines across math, science, and code tasks. They further analyze the structure of the reasoning, noting token-efficient, directed reasoning in models like GPT‑6 Astra, which externalizes only crucial steps while handling elementary ones internally.
ReasoningShield introduces a benchmark and lightweight models for detecting unsafe content in the intermediate reasoning steps of Large Reasoning Models (LRMs). The benchmark contains 9.2K annotated (Query, CoT) pairs across 10 risk categories, 3 safety levels, and 8 LRMs, and the proposed models achieve 91.8% F1, outperforming existing moderation tools by significant margins. The study highlights that current moderation tools degrade by up to 35.2% on Chain-of-Thought reasoning compared to traditional answer moderation.
arXiv:2608. 03291v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process.
LiveMathematicianBench is a dynamic multiple‑choice benchmark for research‑level mathematical reasoning, built from recent arXiv papers published after model training cutoffs. It introduces a thirteen‑category logical taxonomy of theorem types and uses a proof‑sketch‑guided distractor pipeline to create plausible but invalid answer choices, enhancing sensitivity to genuine reasoning. Evaluation shows current large language models perform poorly, with the best model scoring 43.5% overall and only 17.6% under substitution‑resistant conditions, indicating the benchmark’s difficulty and realism.
The paper introduces Tool Primitives, a design that replaces rigid API schemas with natural language interfaces for tool calling, enabling seamless inter-tool communication. It builds ToolFace, a repository of over 25,000 functions that LLMs can dynamically retrieve, and HEART, a harness engineering framework that orchestrates tool use with planning, routing, and verification. Experiments show HEART outperforms fine‑tuned models and leading commercial LLMs while cutting API costs by up to 85%.
ToolGate is an executable acceptance pipeline designed to streamline the creation of scientific benchmarks that rely on specialist software. It evaluates each model-generated item through three gates: (1) an executable solution script must reproduce the proposed answer, (2) a randomized no‑tool screen rejects items solvable without the software, and (3) a tool‑using agent must solve the item within a time limit. In a FEniCSx instantiation, 500 generation attempts produced 128 unique, verified benchmark items after successive filtering.
arXiv:2607. 12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny.
arXiv:2606. 05402v1 Announce Type: cross Abstract: Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the reasoning process.
arXiv:2605. 03344v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems such as math and code generation.