The paper introduces SALA, a Semantic‑Aware Logical Alignment framework designed to improve demonstration selection for complex reasoning in in‑context learning. SALA learns task‑specific reasoning operations, embeds them into a continuous semantic space, and applies dynamic time warping to flexibly align reasoning sequences, offering soft matching and interpretability. Experiments on four reasoning benchmarks with three large language models show that SALA outperforms existing methods, and analysis highlights the importance of operation induction and logical semantic alignment.
arXiv:2605. 13511v3 Announce Type: replace-cross Abstract: While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks.
arXiv:2601. 03506v2 Announce Type: replace-cross Abstract: Recent large reasoning models (LRMs) have achieved strong performance on complex reasoning tasks by generating a long chain-of-thought (Long-CoT).
The paper introduces Prototype-Mediated Process Supervision (PMPS), a method that uses learnable reasoning prototypes to provide structural supervision for latent chain-of-thought embeddings, addressing representation collapse and uneven information distribution. PMPS aligns latent and explicit CoT embeddings in a shared prototype space via many-to-many soft assignment and employs a Progressive Sequential Alignment module to guide training from positional priors to adaptive matching. Experiments show PMPS reduces output token length to under 50% of explicit CoT on GSM8K-Aug and improves accuracy by 2.08% over SIM-CoT, even surpassing CoT-SFT on GPT-2 and achieving the highest accuracy among latent reasoning methods on larger models and harder tasks.
arXiv:2602. 23161v4 Announce Type: replace Abstract: Time series reasoning demands both the perception of complex dynamics and logical depth.
SPEAR (Symbolic Process Evaluation and Alignment Reward) is a training‑free, plug‑and‑play reward method for on‑policy distillation in reinforcement learning. It converts natural‑language reasoning traces into domain‑adaptive symbolic milestones and uses the longest common subsequence to align student exploration with teacher milestones, producing a dense, order‑aware reward that enforces logical consistency without an external neural verifier. Experiments on math, science, and commonsense reasoning tasks show that SPEAR effectively bridges the reasoning gap between student and teacher models through sequence‑level distillation with efficient dense process rewards.
arXiv:2604. 10788v2 Announce Type: replace-cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning.
PARTAB is a framework that improves large language model reasoning on tables by constructing a structured evidence interface. It represents query‑relevant evidence as semantically coherent, row‑linked table regions and performs hierarchical selection over column groups and row‑level partitions before composing the evidence for answer generation. Evaluations on multiple table reasoning benchmarks show that PARTAB consistently outperforms full‑table prompting and recent methods, achieving strong performance on WikiTableQuestions and TabFact while remaining competitive on numerical reasoning tasks.
arXiv:2608. 03204v1 Announce Type: cross Abstract: Post-training reinforcement learning (RL) algorithms are commonly used to align large vision-language models (LVLMs) with human intent and the requirements of visual reasoning tasks.
arXiv:2505.16782v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT...
K2-V2 is a fully open, 360‑open large language model built from scratch, designed to serve as a superior base for reasoning adaptation while also supporting conversation and knowledge retrieval. It competes with leading open‑weight models in its size class, outperforming Qwen2.5‑72B and approaching Qwen3‑235B, and incorporates domain knowledge, reasoning, long‑context handling, and tool use throughout training. The authors release the complete training history, data composition, model weights, and LLM360 artifacts to enable community use and continuous training.
MMEmb-R1 is a multimodal embedding framework that enhances reasoning by treating it as a latent variable and selecting beneficial reasoning paths through pair-aware selection and counterfactual intervention. It uses reinforcement learning to invoke reasoning only when necessary, reducing unnecessary computation and latency. On the MMEB-V2 benchmark, MMEmb-R1 achieves a state‑of‑the‑art score of 71.2 with just 4 B parameters.
arXiv:2607. 01585v1 Announce Type: cross Abstract: Predicate invention (PI), the creation of new predicates to extend the hypothesis space, remains a critical bottleneck in Inductive Logic Programming (ILP).