Search: “test-time-training”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

How well do agents use test/verification techniques?

Dan Luu's eval finds coding-agent testing instructions (TDD, formal methods, PBT, skills) mostly fail to beat defaults on Zstd implementation correctness.

The author ran 26 prompt conditions plus 4 skills on a Zstd-in-Rust implementation eval using codex with GPT-5.6, testing TDD, fuzzing, property-based testing, formal methods (Lean 4, TLA+, Verus, Kani, SMT solvers) and community skills. Nothing dramatically outperformed the default no-instruction condition, which did above average; at xhigh effort, fuzzing and PBT conditions did slightly better than formal methods. Pre-registered predictions included TDD underperforming and popular test skills (ECC, Hegel, Trail of Bits) not outperforming. Results are averages of 80 runs per condition plotted against cost.

Hacker News · security·Sep 8, 02:58 UTC · 8d agoAI researchHN 131↑ · 50 comments

38

Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning

HybridAL is an active-learning training schedule that switches from retraining to fine-tuning on stabilization signals, saving up to 49% time.

Researchers find that choosing between retraining from scratch and fine-tuning is an exploitable decision variable in active learning: retraining helps in early rounds while fine-tuning is safer once the model trajectory stabilizes. HybridAL monitors an online stabilization signal using spectral exponent change and accuracy change, switching from retraining to fine-tuning after sustained stabilization. Across three encoder backbones and six text-classification tasks with five seeds each, HybridAL keeps endpoint macro-F1 non-inferior within a 0.010 margin, saves up to 49% of retraining time, and improves the time-calibration trade-off measured by negative log-likelihood.

Hugging Face daily papers·Sep 5, 20:00 UTC · 11d agoAI research

20

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

Study finds zero-shot time-series foundation models underperform on CGM forecasting; fine-tuned Chronos-Bolt cuts RMSE up to 18.4% and dietary context adds signal.

The paper evaluates time-series foundation models for continuous glucose monitoring forecasting across eight public datasets covering Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol, zero-shot foundation models did not consistently outperform baselines like Elastic Net and PatchTST, but lightweight fine-tuning did, with fine-tuned Chronos-Bolt reducing RMSE by 6.5%-18.4% in the T1D cohort and 8.6%-18.2% in the non-diabetes/T2D cohort. A residual-based fusion framework adding dietary context from CGMacros reduced overall RMSE by about 3% and postprandial RMSE by about 15% versus CGM-only baselines.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:43 UTC · 6d agoAI research

28

Learning Length-Extrapolatable Recurrent Models

Researchers propose Credit Stabilization through Time, a training method letting recurrent models extrapolate up to 128x their training length.

The paper argues that length extrapolation failure in BPTT-trained recurrent models is better explained through state credit, the signal through which future losses reach earlier recurrent states. It introduces Credit Stabilization through Time (CST), which locally rescales the state-credit signal during backpropagation without rotating the corrected component or changing forward computation. Controlled experiments show improved performance beyond the training horizon, with gains at up to 128x the training length.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:59 UTC · 8d agoAI research1

25

ExecCritic: Learn to Test, Test to Improve for Coding Agents

ExecCritic separates test generation from patching for coding agents, lifting SWE-bench Verified resolution to 72.6%.

ExecCritic pairs a test-verify-revise scaffold with role-specific reinforcement learning: a Test agent writes repository-native tests and a Repair agent fixes code from execution feedback, both using Qwen-3.5-35B-A3B backbones. Post-trained Qwen agents compose to 72.6% on SWE-bench Verified, an 11.4-point gain over the 61.2% no-test baseline, without stronger-model or oracle feedback at evaluation time. The work shows test quality is the key variable: base-agent tests lowered resolution to 57.3% while GPT-5.6-sol tests raised it to 65.3%.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:53 UTC · 8d agoAI research1

36

Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

Exploration-guided prompt scaffolding rewrites training prompts by Exploration Potential Score, boosting multimodal RL post-training accuracy up to 11.5%.

The paper proposes dynamically adapting the training prompt distribution during online RL post-training of multimodal LLMs using the Exploration Potential Score (EPS), a lightweight rollout-based proxy for prompt utility computed from on-policy statistics with no additional overhead. Rather than discarding low-utility prompts, a teacher model generates scaffolded rewrites that preserve task intent while making training more informative. Integrated with GRPO on Geo3K and MMK12, the method achieves up to 9.7% relative in-domain improvement plus 11.5% on MathVision and 11.1% on MMMU-Pro.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI research

35

Revisiting Complete Reasoning Traces for Post-Training

Researchers show full reasoning traces provide limited benefit in LLM post-training, with heavily truncated or endpoint-only trajectories performing comparably.

A pilot study plus attention-based analyses and controlled token-removal studies show intermediate tokens in reasoning trajectories contribute minimally to final reasoning quality. Partial trajectories remain effective even under heavy truncation, and training on endpoints alone leads to consistent changes in reasoning behavior. The finding also benefits reinforcement-learning and on-policy distillation post-training; code is released at github.com/naver-ai/revisiting-trace.

Hugging Face daily papers·Sep 6, 20:00 UTC · 10d agoAI research

32

Inoculation Midtraining with Learned Neologisms

Inoculation Midtraining confines unsafe LLM behavior to a neologism-marked context, reducing misalignment after unsafe post-training but leaking under nearby contextual cues.

The paper introduces Inoculation Midtraining, which teaches a base model during midtraining that unsafe behavior belongs to a context marked by a learned neologism token, then post-trains on unsafe data within that context. Across supervised fine-tuning and RL post-training regimes, the technique reduces misalignment while preserving transfer of benign properties like German or Shakespearean prose. However, it does not outperform standard Inoculation Prompting, is sensitive to training configuration, and produces a leaky boundary that nearby contextual cues can reactivate. The authors conclude it is not yet a load-bearing component of a developer safety framework.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:12 UTC · 2d agoAI safety & security

42

Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation

A distillation framework compresses LLM reasoning into a 15.5M-parameter trade-up recommendation model reaching AUC 0.941 with product-type test-time training.

The paper targets trade-up recommendation, which identifies higher-quality alternatives that preserve customer purchase intent. A retrieval-augmented few-shot LLM teacher generates labels and rationales that supervise a compact embedding-pair classifier; at inference the 15.5M-parameter student uses only two precomputed 768-dimensional embeddings with no LLM calls. On 8,352 annotated pairs, label-only training scored AUC 0.912, reasoning distillation reached 0.924, and product-type test-time training lifted it to 0.941 with average precision 0.940. The distilled student is roughly 5,000x faster and 10,000x cheaper than direct LLM inference on a 100K-pair proxy catalog.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:08 UTC · 12d agoAI research

25

When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis

Elo-per-token analysis shows LLM agents' marginal gains drop below independent sampling at scale; parallel sessions beat one long session.

The paper proposes Elo-per-token analysis, using a Bradley-Terry model to measure how agent performance scales with token budget on open-ended tasks with continuous scoring. Across four agents and four benchmarks with sessions up to 100M tokens, agents initially convert tokens to Elo faster than independent sampling but eventually slow below the linear-in-log-compute reference. The authors define a scaling inflection point and show that splitting 100M tokens across parallel sessions on FrontierCS Polyomino Packing gains +264 Elo over one long session and +355 over ten short sessions. Human contestants on shared AtCoder Heuristic Contest tasks improve superlinearly, indicating headroom over current agents.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI research3· 2 reads

48

[AINews] 10% worse, 100x cheaper, 10000x faster: Why Simulation is taking over

Latent Space argues AI training pipeline stages—rewards, data, teachers, curricula, environments—are flipping from human-made to model-made simulation.

Latent Space's AINews essay traces how each component of AI training has turned synthetic since 2022: reward models (InstructGPT, RLAIF), synthetic pretraining data (Microsoft Phi, NVIDIA Nemotron-4 340B), model teachers (Alpaca, DeepSeek-R1 distillation), and self-generated curricula (Self-Rewarding Language Models, SPIN). In 2026 it highlights Karpathy's autoresearch loop—700 experiments yielding 20 kept improvements, cutting GPT-2 training time from 2.02 to 1.80 hours—and Z.ai's GLM-5.3 fully synthetic RL environment, judging, and verification stack. It frames these shifts as 'simulation': 10% worse but 100x cheaper and 10,000x faster than human equivalents.

Latent Space·Aug 22, 07:36 UTC · 25d agoAI industry

35

5 useful things you'll learn in my new post-training textbook (shipping now!)

Nathan Lambert's new RLHF and post-training LLM textbook covers PPO, GRPO, GSPO, CISPO and related techniques, freely available online.

Nathan Lambert's book 'Reinforcement Learning from Human Feedback: Aligning and Post-training LLMs' is now shipping from Manning. It covers policy-gradient algorithms including PPO, GRPO, GSPO, CISPO, and RLOO, plus loss aggregation, truncated importance sampling, asynchronous RL systems, and post-training topics like rejection sampling, outcome reward models, and on-policy distillation. The book is freely available online with a 12-hour course, codebase, and exercises.

Interconnects·Aug 10, 13:02 UTC · Aug 10, 2026AI research

28

Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback

CCL couples teacher calibration with student updates via token-level branching, provably removing teacher bias in LLM distillation.

The paper proposes Coupled Calibration and Learning (CCL), an LLM distillation algorithm that alternates teacher calibration using source-question reward feedback with student training on target questions under covariate shift. Each iteration calibrates the teacher on source feedback, trains the student on target questions, and lets the updated student inform subsequent calibration. The authors prove the student's expected KL divergence to the oracle student converges to zero at a polynomial rate, and show regularized direct matching error can remain bounded away from zero.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:15 UTC · 1d agoAI research

20

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

TGOPD verifies teacher reliability per prompt before on-policy distillation, outperforming vanilla OPD across math, code, and instruction benchmarks.

Teacher-Gated On-Policy Distillation (TGOPD) estimates teacher reliability from verifier-scored teacher probes and routes each prompt either to dense on-policy distillation or to verifier-grounded GRPO, avoiding misleading updates from confidently wrong teachers under mode-seeking reverse KL. Across 4B and 35B students in mathematics, code, and instruction following, TGOPD outperforms vanilla OPD in all six single-domain settings and achieves higher seven-benchmark averages under multi-domain training. It also raises teacher-node GPU utilization from 9.8% to 78.9% in the measured 4B single-domain run by reusing idle teacher capacity.

Hugging Face daily papers·Sep 1, 20:00 UTC · 15d agoAI research

26

Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks

Researchers propose Feedback-Enriched Environments (FEEs) that reduce reward sparsity and improve RL training of Qwen3-based agents on SciWorld and BFCL.

The paper proposes shifting from agent-side warmup (SFT) to environment-side adaptation via Feedback-Enriched Environments to address severe reward sparsity in RL training of long-horizon LLM agents. A pilot study defines a feedback strategy that transitions from action guidance to observation enrichment in later training stages. Large-scale experiments on SciWorld and BFCL across Qwen3 model scales and GRPO, GSPO, and DAPO show consistent gains, plus stabilized training dynamics and proactive exploration.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI research

25

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

T1, a 122B MoE terminal agent trained with reinforcement learning, reaches 64.0% on Terminal-Bench 2.1, surpassing GPT-5.4 and GLM-5.1 on long-horizon tasks.

T1 is a 122B mixture-of-experts model trained with reinforcement learning to operate a real shell in a cloud sandbox for up to 300+ tool-call turns per task, rewarded by executing each task's own verifier. The recipe combines aggressive warm starts, dense process rewards, TITO construction, and rollout routing replay, cutting the training-to-inference log-probability difference from 0.021 to 0.013 with zero token drift. Training used an out-of-distribution corpus disjoint from Terminal-Bench 2.1. Post-training raised the base model from 43.8% to 64.0% resolved on Terminal-Bench 2.1 and 27.9% on Long-Horizon Terminal Bench.

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research1

55

Learning to Coach for Experiential Learning

Learning to Coach trains a dedicated LLM coach to extract transferable experiential knowledge from a frozen actor's trajectories, beating self-refinement.

Learning to Coach (L2C) trains an LLM-as-a-Coach to extract actionable experiential knowledge from a frozen actor model's previous solution trajectories, optimizing rewards based on the actor's guided response correctness. It studies same-instance and cross-instance rewards, where cross-instance elicits knowledge that transfers to other problems. Across mathematical reasoning and interactive text-games, L2C outperforms self-refinement and untrained coaches, scales better with extra inference iterations than larger decoding budgets, and transfers to out-of-distribution tasks.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 16:47 UTC · 2d agoAI research1

20

Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning

CoTS temperature scaling cuts test-time prompt tuning's expected calibration error from 11.90% to 5.38% on ImageNet variants while raising accuracy.

The paper proposes CoTS, a post-hoc calibration method that applies temperature scaling to minimize the confidence gap between test-time-adapted and zero-shot predictions. A weak-strong ensemble variant, E-CoTS, further exploits multiple test-time augmentations to boost accuracy while maintaining calibration. E-CoTS reduces average expected calibration error from 11.90% to 5.38% on ImageNet variants while increasing accuracy from 60.74% to 62.95%.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 16:25 UTC · 1d agoAI research

20

Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR

Researchers propose DATPO, a difficulty-adaptive tree-structured RLVR training method that expands reasoning coverage (pass@k) and improves test-time scaling on math benchmarks.

The paper identifies three rollout design principles for RLVR: difficulty-adaptive rollout expands pass@k, tree-based rollout beats parallel sampling, and sentence-entropy-guided forking overcomes token-level branching localization. DATPO combines difficulty-adaptive tree search with a sibling-diversity advantage term to promote semantic diversity during training. On mathematical reasoning benchmarks, DATPO outperforms baselines in pass@k, directly translating to superior test-time scaling performance.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI research

30

Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision

ECCV 2026 challenge winner reformulates egocentric intervention timing as single-token classification, boosting macro-F1 by 0.249 over free-form generation.

The paper describes the winning submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, ranking first in the large-model division and second in the <=2B division. The method reformulates intervention timing as single-token yes/no classification, improving macro-F1 by 0.249 and G-mean by 0.30 over free-form generation. Supervision generated by a tool-calling video agent transferred better than a narration-only dataset that was four times larger and ten times cheaper, suggesting visual grounding matters more than annotation volume.

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research

22

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

WearableQA benchmark tests LLM health reasoning over longitudinal wearable data; the best of 14 evaluated LLMs reaches 72.9% accuracy.

WearableQA comprises 4,084 ten-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning. Evaluation of 14 proprietary and open-source LLMs shows performance from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:52 UTC · 12d agoAI research

14

Learning never stops: How AI makes learning continuous

OpenAI report describes how students and educators use ChatGPT to extend learning continuously beyond the classroom.

OpenAI published a report examining how students and educators use ChatGPT to make learning more continuous. The report describes support that extends beyond the classroom, positioning ChatGPT as an ongoing learning companion. The release is part of OpenAI's education-focused communications rather than a technical or safety research paper.

OpenAI News·Aug 26, 10:00 UTC · 21d agoAI industry

15

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Composing data, function, and weight anchors with merged LoRA raises 100-task long-horizon retention from 1.2% to 34.9% in continual fine-tuning.

The paper introduces long-horizon memorization: a model learns 100 query-answer tasks through continual supervised fine-tuning without retaining earlier examples or receiving task identifiers at inference. No single continual learning mechanism maintains strong retention at this horizon, so the authors compose complementary mechanisms along data/function/weight anchors and low-rank allocation rules. The best method combining all three anchors with merged LoRA ranks among the top 3 methods on all three datasets and raises average final retention from 1.2% to 34.9%, a 28-fold improvement.

Hugging Face daily papers·Sep 6, 20:00 UTC · 10d agoAI research

42

Google's new AI model predicts the future from sales data, weather, and discount schedules

Google Research released TimesFM-3, a 330M-parameter multivariate time series forecasting model that tops Gift-Eval, FEV-Bench, and Time benchmarks and is on Hugging Face.

Google Research released TimesFM-3, a 330-million-parameter Transformer-based time series forecasting model trained on more than one trillion real and synthetic data points. It works zero-shot and adds multivariate support, ingesting related series, historical-only covariates, and known future events such as discount schedules and weather forecasts, while filling all future time steps in a single one-shot pass. Google reports first place among pretrained forecasting models on Gift-Eval, FEV-Bench, and Time, ahead of Amazon's Chronos-2, the Toto-2.0 family, and its own TimesFM-2.5. Weights are available on GitHub and Hugging Face, with BigQuery integration planned in the coming weeks.

The Decoder·Sep 12, 09:26 UTC · 4d agoModel release2

48

Competence-Gated Pooling of Language Models and Priors for Event Forecasting

Paper proposes a competence gate pooling language model forecasts with external priors, improving Brier score from 0.0771 to 0.0732 across 2,357 binary questions.

The paper defines a language model's relative competence as its marginal value beyond an available external forecast, and derives conditions under Brier loss where model disagreement improves that forecast. A competence gate estimates domain-level source weights from resolved outcomes, shrinks uncertain estimates toward a global weight, and recalibrates the pooled forecast. Across 2,357 resolved binary questions and five language models, it improves the external baseline from 0.0771 to 0.0732 Brier and beats global forecast combinations, though it defers to the market on ForecastBench. Across four Qwen models, verbal confidence failed to identify when the model outperformed the external forecast, while outcome-estimated competence supported better abstention.

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research

38

Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics

Researchers model curriculum learning as Wasserstein transport over difficulty distributions, finding curriculum benefits are strongly task- and budget-dependent with no dominant strategy.

The framework represents curricula as trajectories of training distributions over discrete difficulty levels, decoupling ordering, matched exposure, endpoint smoothness, and pacing. Across a calibrated suite of 12 tasks and 33 difficulty axes under fixed training budgets, no single strategy dominates, though easy-to-hard ordering improves hard-level performance relative to exposure-matched static sampling. Endpoint smoothness and pacing substantially affect where along the difficulty spectrum a curriculum is effective, and the transport view supports extensions to learned pacing and structured difficulty spaces.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:39 UTC · 8d agoAI research1

28

Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models

Latent Interface Training improves robot foundation model generalization by constraining visual conditioning, boosting LIBERO-Plus success up to 10.7 points.

The paper identifies vision-action shortcuts where robot policies exploit task-irrelevant visual cues that fail under distribution shift. Latent Interface Training (LIT) first trains an action expert conditioned on language, robot state, and terminal SE(3) end-effector poses without images, then constrains visual input through a pose-supervised latent interface. Across four VLA and world-action architectures (Pi0.5, MolmoAct2, FAST-WAM, ImageWAM), LIT improves LIBERO-Plus success by 3.87-10.70 percentage points. Real-world tests show 13.30-16.70 percentage-point gains under unseen cameras, lighting, and distractors.

Hugging Face daily papers·Sep 10, 20:00 UTC · 6d agoAI research

32

Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation

Researchers propose ERPO, enabling test-time reinforcement learning for code generation via probe-executed consensus rewards, rank masking, and entropy regularization.

The paper introduces probe-driven test-time reinforcement learning (TTRL) for code generation, where output-free probe inputs are constructed from problem statements and candidate programs are executed on them to compute a Probe Consensus Reward (PCR). Because PCR can be gamed through spurious consensus, the authors propose Entropy-Regularized Rank-Masked Policy Optimization (ERPO), which turns low-PCR outcomes into conservative negative updates via rank masking and constrains policy drift with an entropy ceiling. On coding benchmarks, ERPO substantially improves pass@1 and pass@k in both in-domain adaptation and zero-shot transfer.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:54 UTC · 8d agoAI research1

38

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

WearableQA benchmark introduces 4,084 questions over real longitudinal wearable data, showing 14 LLMs score 19.6-72.9% on health reasoning, far from solved.

WearableQA is a benchmark of 4,084 10-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning, using a dual-grounding framework combining literature and population-validated patterns. Evaluations of 14 proprietary and open-source LLMs show accuracy ranging from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.

Hugging Face daily papers·Sep 3, 20:00 UTC · 13d agoAI research

35

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

A controlled pure-autoregressive testbed shows task-specific validation losses rank image tokenizers differently, with I2T loss the most consistent signal.

Researchers built a controlled pure-autoregressive testbed and tracked task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. They find losses should be analyzed per task because they exhibit distinct scaling behavior and rank tokenizers differently, and that the loss-performance relationship depends on the predicted token space. I2T loss, computed over a shared text vocabulary, correlates consistently with both generation and visual understanding performance after supervised finetuning. Case studies revisit the discriminator, semantic supervision, and vocabulary size as tokenizer design axes.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:57 UTC · 8d agoAI research1

30