Articles tagged
llm
16 articles
SkillOpt: Training Agent Skills Like Neural Network Weights - Without Touching the Model
SkillOpt applies deep-learning-style optimization - bounded edit budgets, validation gating, rejected-edit memory - to natural-language skill documents, improving frozen LLMs by up to +39 points across 52/52 evaluated cells without changing a single model weight.
TAPS: Why Your Draft Model's Training Data Matters More Than Its Architecture
TAPS shows draft training data drives speculative decoding: merged-tree verification of math and chat specialists hits 5.11 acceptance length, weight averaging 2.59.
Lost in Stories: How LLMs Lose the Thread in Long Narratives
ConStory-Bench measures consistency in 10,000-word stories: GPT-5-Reasoning leads with 0.113 errors per 10k words, and its checker finds 3.2x more bugs than experts.
SAGE: Your Reasoning Model Knows When to Stop Thinking — You Just Won't Let It
SAGE scores reasoning paths by cumulative log-probability instead of next-token probability, letting models stop thinking 40-50% earlier at equal or better accuracy.
OPUS: How to Train LLMs 6x Faster by Choosing the Right Data
OPUS scores every sample by alignment minus redundancy in optimizer update space; on Qwen3-8B it beat full 3B-token training using 0.5B, at 4.7% extra compute.
AI Co-Scientist: Teaching Models to Write Research Plans Better Than Humans
Rubrics mined from papers turn a frozen grader into an RL reward; experts preferred the generated research plans 70% over baseline and 52% over published ones.
Comp-LLM: When an Army of Experts Beats a Giant – An Analysis of a Revolution in AI Architecture
Comp-LLM routes a query as a DAG of sub-queries to parallel experts: about 35B scores 0.83 F1 to Llama-2 70B's 0.85, and 1.1-1.7x faster than sequential agents.
Cost-Constrained LLM Cascades — Meet C3PO
C3PO runs LLM cascades under a probabilistic cost constraint: stay in budget with 95% confidence, escalating to a bigger model only when the cheap one falls short.
DIALTREE‑RPO — a simple guide to 'Tree‑based Dialogue Reinforced Policy Optimization'
Friendly explanation of 'Tree‑based Dialogue Reinforced Policy Optimization for Red‑Teaming Attacks' — with examples and LaTeX formulas.
Attention as a Compass – Teaching Reasoning Models to Explore Smarter
AttnRL uses a model's own attention to pick branching points in process-supervised RL, beating GRPO and TreeRL by 1.8 points on math while cutting training time 8%.
The Anatomy of AI Lies: How Language Models Can Deceive Us
Can LLMs Lie? traces deception to layers 10-15 with logit lens, zero-ablation and steering vectors: models rehearse lies in dummy tokens; bigger models lie better.
Look Inside Seamless Flow's Hyper-Efficient Training
Seamless Flow kills RL pipeline bubbles with a data plane and tag-driven GPU scheduling: up to 100% more throughput than VERL, and 23.0% to 45.8% on SWE-Bench.
Dynamic Fine-Tuning (DFT): How a Single Line of Code is Revolutionizing AI Training
Dynamic Fine-Tuning rescales each token loss by the inverse of its probability, a one-line change that beats SFT on generalization and rivals offline RL methods.
A Deep Dive into the Text-to-SQL Revolution: Analyzing the Adaptive Method
Adaptive Text-to-SQL splits the work in two: a Selector retrieves conceptually similar question-schema-SQL triples, a Generator writes the query in-context.
Goedel-Prover-V2: A Revolution in Automated Theorem Proving
Goedel-Prover-V2 learns from scaffolded proof sketches and its own failed Lean attempts, outperforming AlphaProof and DeepSeek-Prover on miniF2F and PutnamBench.
RetrySQL: Self-Correcting Query Generation
RetrySQL injects deliberate wrong reasoning steps and a BACK token into text-to-SQL pretraining, lifting OpenCoder 1.5B execution accuracy by 4 points toward GPT-4o.