Challenge: Existing models with long chain-of-thought reasoning lack reasoning depth and domain-specific utility.
Approach: They propose a model merging framework that integrates reasoning with domain-specific task models.
Outcome: The proposed model merging framework outperforms state-of-the-art models while maintaining robust reasoning performance.

Similar Papers

Superficial Self-Improved Reasoners Benefit from Model Merging (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) rely heavily on large-scale reasoning data, but as data becomes scarce, model self-improvement offers a promising alternative.
Approach: They propose to merge the weights of original and self-improved LLMs to mitigate model collapse and improve generalized reasoning capability.
Outcome: The proposed model merge mitigates model collapse and improves generalized reasoning capability.
Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: a zero-shot merging framework for large language models consolidates specialized domain experts into a single model without any further training.
Approach: They propose a zero-shot merging framework that consolidates specialized domain experts into a single model without further training.
Outcome: Experiments on code generation, mathematical reasoning, medical question answering, and instruction-following benchmarks confirm the versatility and effectiveness of the proposed framework.
Enhancing Multilingual Reasoning via Steerable Model Merging (2026.findings-acl)

Copied to clipboard

Challenge: Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model.
Approach: They propose a model merging framework that modulates the contribution of each source model.
Outcome: Experiments show that the proposed model merging framework outperforms strong baselines on multilingual reasoning benchmarks across 21 different languages.
Beyond ’Aha!’: Toward Systematic Meta-Abilities Alignment in Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Challenge: Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as self-correction, backtracking, and verification.
Approach: They explicitly align large reasoning models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks.
Outcome: The proposed model aligns models with deduction, induction, and abduction meta-abilities using automatically generated, self-verifiable tasks.
Logit Arithmetic Elicits Long Reasoning Capabilities Without Training (2026.findings-acl)

Copied to clipboard

Challenge: Large reasoning models exhibit long chain-of-thought reasoning with complex strategies such as backtracking and self-verification, yet, these capabilities typically require resource-intensive post-training.
Approach: They propose a decoding-time approach which transfers long chain-of-thought reasoning capabilities from a substantially smaller reasoning guider to a large non-reasoning target.
Outcome: The proposed method improves performance over a model 21x smaller than the target model by 21.5% and 24.2% over the model.
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches restrict students to following a single golden rationale and treat different reasoning paths independently, causing suboptimal performance.
Approach: They propose a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction and employ a feedback-driven inertia calibration mechanism to align supervision with the student’s current adaptability.
Outcome: Experiments show that the proposed framework achieves state-of-the-art performance on both in-distribution and out-of distribution benchmarks.
LM-Cocktail: Resilient Tuning of Language Models via Model Merging (2024.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models are continually fine-tuned to better support downstream applications. however, this operation may result in significant performance degeneration on general perspectives.
Approach: They propose a method which enables pre-trained language models to stay resilient in general perspectives.
Outcome: The proposed model achieves strong empirical performance in the whole scope of general tasks while preserving a superior capacity in its targeted domain.
ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization (2026.findings-eacl)

Copied to clipboard

Challenge: Large Reasoning Models (LRMs) are powerful but still suffer from inefficient and off-target reasoning.
Approach: They propose a training-free framework that automatically optimizes Large Reasoning Models' reasoning by generating think-prefixes that evolve driven by a taxonomy of reasoning behaviors.
Outcome: The proposed framework significantly improves accuracy-length trade-off for efficient reasoning, drastically improves safety and improves instruction following.
Mergenetic: a Simple Evolutionary Model Merging Library (2025.acl-demo)

Copied to clipboard

Challenge: Recent work shows that combining model merging with evolutionary algorithms can boost performance, but there is currently no library for experimenting with different evolutionary algorithms and merging methods.
Approach: They propose an open-source library for evolutionary model merging that enables easy composition of merging methods and evolutionary algorithms while incorporating lightweight fitness estimators to reduce evaluation costs.
Outcome: The proposed library produces competitive results across languages and tasks using modest hardware.
Exploring Self-supervised Logic-enhanced Training for Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Traditional attempts to enhance the logical reasoning abilities of language models often rely on supervised fine-tuning, limiting their generalization to new tasks or domains.
Approach: They propose a framework for integrating logical reasoning capabilities into LLMs and activating them via in-context learning.
Outcome: The proposed framework achieves comparable results to existing models on three language understanding benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations