efficient-reasoning

Tag

Cards List
#efficient-reasoning

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning

arXiv cs.CL · 2026-07-20 Cached

Proposes BIRD, a two-stage self-reasoning distillation method that bootstraps concise reasoning trajectories before on-policy training, achieving stronger accuracy-efficiency trade-offs on MATH-500 and AIME benchmarks. On Qwen3-8B, accuracy improves from 86.2% to 92.0% while average response length drops from 3,099 to 1,115 tokens.

0 favorites 0 likes
#efficient-reasoning

Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026

arXiv cs.CL · 2026-07-13 Cached

This paper presents a task-specific two-agent architecture for multimodal question answering in the QANTA 2026 shared challenge, using GPT-4.1-mini for tossup questions with confidence calibration and GPT-4.1 for bonus questions with structured reasoning. The system achieved the highest overall leaderboard score, demonstrating the effectiveness of efficient reasoning strategies.

0 favorites 0 likes
#efficient-reasoning

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models

arXiv cs.CL · 2026-07-02 Cached

CAT introduces a framework that leverages model self-certainty signals to autonomously adjust reasoning length based on problem difficulty, reducing overthinking and improving inference efficiency for large reasoning models.

0 favorites 0 likes
#efficient-reasoning

@_akhaliq: paper:

X AI KOLs Following · 2026-06-23 Cached

This technical report presents Ling-2.6 and Ring-2.6, a family of trillion-parameter models designed for efficient and instant agentic intelligence, featuring architectural upgrades like hybrid linear attention and specialized training methods including KPop reinforcement learning. All checkpoints are open-sourced.

0 favorites 0 likes
#efficient-reasoning

SuCo: Sufficiency-guided Continuous Adaptive Reasoning

arXiv cs.CL · 2026-06-17 Cached

Introduces SuCo, a two-stage training framework for Large Reasoning Models that uses the concept of Minimal Sufficient CoT to reduce reasoning tokens while improving accuracy across math, code, and science benchmarks.

0 favorites 0 likes
#efficient-reasoning

Language Models Need Sleep

Hacker News Top · 2026-05-26 Cached

This paper introduces a sleep-like consolidation mechanism for Transformer-based LLMs that periodically converts recent context into persistent fast weights in SSM blocks, clearing the KV cache to improve long-horizon reasoning without increasing inference latency.

0 favorites 0 likes
#efficient-reasoning

HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models

arXiv cs.AI · 2026-05-26 Cached

This paper proposes HyperGuide, a method that distills reasoning progress into a hyperbolic geometric signal to guide step-by-step generation in LLMs, improving multi-step reasoning efficiency without explicit tree search.

0 favorites 0 likes
#efficient-reasoning

@jinyuhou0: On popular benchmarks, our 30B model matches systems 20-30x its size (gpt-5.4-xhigh, DeepSeek-V3.2, Kimi-K2.5), while u…

X AI KOLs Timeline · 2026-05-22 Cached

A new 30B model matches systems 20-30x its size on popular benchmarks while using up to 95% fewer reasoning tokens than comparable agentic LLMs, achieved through a learned configurator that decides when and how to reason. Model and code are openly available.

0 favorites 0 likes
#efficient-reasoning

@mdeng34: Frontier LLMs are converging on efficient, adaptive reasoning. Opus 4.7 lets the model decide how deeply to reason. GPT…

X AI KOLs Timeline · 2026-05-22 Cached

New research introduces SR²AM, a configurator that self-regulates when to use simulative reasoning, improving efficiency and performance in LLMs.

0 favorites 0 likes
#efficient-reasoning

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

Hugging Face Daily Papers · 2026-05-21 Cached

Introduces SR²AM, a framework for efficient agentic reasoning via self-regulated simulative planning, achieving competitive performance with models 20-30x larger while using 26-95% fewer reasoning tokens.

0 favorites 0 likes
#efficient-reasoning

Agentic Test-Time Scaling (GitHub Repo)

TLDR AI · 2026-05-12 Cached

AutoTTS is an open-source tool that uses agentic discovery to automatically find optimal test-time scaling strategies for LLMs, significantly reducing token usage and cost through replay-based evaluation.

0 favorites 0 likes
#efficient-reasoning

LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification

arXiv cs.CL · 2026-05-11 Cached

The paper introduces LaTER, a two-stage reasoning paradigm that combines latent exploration with explicit Chain-of-Thought verification to reduce token usage and improve efficiency in large language models without sacrificing accuracy.

0 favorites 0 likes
#efficient-reasoning

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning

Hugging Face Daily Papers · 2026-04-17 Cached

This paper introduces STOP (Super Token for Pruning), a lightweight method that learns to prune unpromising reasoning paths early during parallel decoding by appending learnable tokens and reading KV cache states, achieving 70% token reduction while improving performance on AIME and GPQA benchmarks.

0 favorites 0 likes
#efficient-reasoning

Efficient Reasoning with Balanced Thinking

Papers with Code Trending · 2026-03-12 Cached

This paper introduces ReBalance, a training-free, plug-and-play method that dynamically balances overthinking and underthinking in large reasoning models, improving efficiency and accuracy across multiple benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback