RLCracker is a reinforcement learning attack that erases LLM watermarks at 98.5% success rate with minimal data and generalizes across ten schemes and multiple model sizes.
super hub Mixed citations
s1: Simple test-time scaling
Mixed citation behavior. Most common role is background (67%).
120
Pith papers citing it
Background
67% of classified citations
abstract
Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance. First, we curate a small dataset s1K of 1,000 questions paired with reasoning traces relying on three criteria we validate through ablations: difficulty, diversity, and quality. Second, we develop budget forcing to control test-time compute by forcefully terminating the model's thinking process or lengthening it by appending "Wait" multiple times to the model's generation when it tries to end. This can lead the model to double-check its answer, often fixing incorrect reasoning steps. After supervised finetuning the Qwen2.5-32B-Instruct language model on s1K and equipping it with budget forcing, our model s1-32B exceeds o1-preview on competition math questions by up to 27% (MATH and AIME24). Further, scaling s1-32B with budget forcing allows extrapolating beyond its performance without test-time intervention: from 50% to 57% on AIME24. Our model, data, and code are open-source at https://github.com/simplescaling/s1
hub tools
citation-role summary
background 12
baseline 2
method 1
citation-polarity summary
claims ledger
- abstract Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance. First, we curate a small dataset s1K of 1,000 questions paired with reasoning traces relying on three criteria we validate through ablations: difficulty, diversity, and quality. Second, we develop budget forcing to control test-time compute by forcef
authors
co-cited works
representative citing papers
Shared token budgets between visible chain-of-thought and answers create a coupling tax that makes non-thinking competitive on math benchmarks, with a truncation decomposition predicting the crossover and split budgets improving results.
GIANTS-4B, trained with RL on a new 17k-example benchmark of parent-to-child paper insights, achieves 34% relative improvement over gemini-3-pro in LM-judge similarity and is rated higher-impact by a citation predictor.
In-distribution sampling across 25 models and controlled interventions with DAG-verified content show that semantic reasoning and validation content, not token count, drive CoT gains.
KCSAT-ML benchmark supplies human error rates for math problems and DRG metric exposes that model accuracy collapses on high-human-error items while test-time scaling shows non-monotonic gains and alignment failures.
IDPR is a response-conditioned inhibitory deliberation method that trains a controller on fast-slow outcome pairs to decide when to override LLM fast answers, improving accuracy from 47.90% to 48.92% with slow reasoning invoked on only 8.20% of a 5,000-example math test set.
Three problem-level trajectory features derived from the distributional signature of failed LLM rollouts enable failure clustering at 84.3% accuracy and a training-free routing rule that improves rescue by 12.2% on hard cases.
PANDO introduces an online skill-distillation method with a structured library, reflection, demotion, routing, compression, and cache-aware prompting that reaches 58.3% success on 910 VisualWebArena tasks using 58-61% fewer tokens than prior methods.
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
Decoupling prefix source from token-level KL direction in autoregressive sequence KL yields four objectives unifying SFT, DAgger, offline RL and OPD, with KL mixing and entropy-gated curriculum improving math reasoning accuracy and shortening responses.
Language models produce overcomplete reasoning traces where on average 46% of steps can be removed while preserving the answer in 86% of cases, with necessity concentrated in the top three steps.
DUET improves RLVR by allocating tokens across both prompt selection and rollout length, outperforming full-budget baselines even when using only half the tokens.
POSTCONDBENCH is a new multilingual benchmark that evaluates LLM postcondition generation on real code using defect discrimination to assess completeness beyond surface matching.
A single-parameter Tsallis loss continuum unifies SFT and RLVR, derives time-to-escape bounds for cold start, and yields GARL and PAFT estimators that improve performance on QA reasoning tasks.
A new SFT framework for MoE models combines bias-driven sparsification with gated condenser experts to retain long-tailed expert information, outperforming DenseMixer and ESFT by over 2.5% on math reasoning and commonsense QA benchmarks.
A single LLM improves its own reasoning by self-distilling from privileged verified traces as teacher to its question-only student policy, outperforming off-policy distillation and RL on math benchmarks with better token efficiency.
An edge-cloud-expert LLM cascade for telecom knowledge systems minimizes processing cost subject to misalignment-risk bounds via multiple hypothesis testing on knowledge and confidence scores.
PIAST iteratively optimizes few-shot examples in prompts via Monte Carlo Shapley value estimation, outperforming prior automatic prompting methods and setting new SOTA on classification, simplification, and GSM8K with modest compute.
LLMs show strong user bias in role-tagged contexts that is amplified by preference alignment and can be reduced or controlled through targeted fine-tuning and DPO.
Hybrid Bayesian-graph LLM agent reaches competitive performance against large models and achieves 67% win rate against humans in controlled Avalon play, outperforming baselines and human teammates.
A learned continue-thinking token, trained via RL on its embedding alone, improves math benchmark accuracy more than fixed-token budget forcing in a frozen language model.
LCPO trains L1 reasoning models to adhere to prompt-specified CoT lengths, supporting accuracy-compute trade-offs and yielding short reasoning models that outperform larger baselines at matched lengths.
VIDA provides 2,500 visually-dependent ambiguous translation examples and span-level disambiguation metrics; CoT-SFT on LVLMs improves out-of-distribution performance over standard SFT.
Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
citing papers explorer
-
VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.