TraceForge introduces a two‑stage training method that generates reasoning traces in the style of a target model family, using supervised learning followed by adversarial refinement. The system produces traces that are judged as authentic with scores comparable to real traces, and when applied to teacher answers, it improves performance on coding benchmarks such as HumanEval+ and MBPP+. The approach addresses the limitation of existing models that only return answers without detailed reasoning, enabling more transparent and learnable outputs.
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
EKLAV is a method that uses a teacher’s chain‑of‑thought (CoT) reasoning as privileged input while supervising only the final answer. By strategically placing parts of the trace in the prompt, EKLAV improves ranking performance on BRIGHT passage reranking and table‑reranking benchmarks, outperforming full‑trace distillation and answer‑only training. The approach reduces training compute and inference time, and the generated traces show more efficient reasoning patterns.
arXiv:2607. 14552v1 Announce Type: cross Abstract: A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors.
arXiv:2607. 20440v1 Announce Type: cross Abstract: Proprietary large language models (LLMs) entail substantial intellectual and financial investment, making them valuable intellectual property (IP).
arXiv:2604.23238v3 Announce Type: replace-cross Abstract: Distillation via reasoning traces exposes frontier models to adversarial third parties, who can bypass their guardrails and misappropriate th...
arXiv:2610.13996v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not cert...
arXiv:2609.38107v1 Announce Type: cross Abstract: Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning...
The paper introduces a self‑distillation method that leverages answer‑only data to improve large language models (LLMs) after training. By training an inverse reasoning LLM to generate latent chain‑of‑thought traces conditioned on the answer, the authors can perform offline distillation that significantly boosts performance on hard prompts for tasks like Countdown and GSM8K. Additionally, the inverse model serves as an accurate verifier, enhancing best‑of‑n selection accuracy.
arXiv:2607. 06855v1 Announce Type: new Abstract: On-policy distillation is a practical post-training recipe for large language models, supplying dense teacher supervision on the student's own trajectories.
arXiv:2605. 03862v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it.
arXiv:2608. 07885v1 Announce Type: new Abstract: Reasoning modes of language models outperform their non-reasoning counterparts on multi-step agentic tasks, but pay a 3-6x premium in output tokens on every episode -- much of it spent re-deriving procedures that are shared across episodes of the same domain.
arXiv:2607. 07690v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (e.