TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksFor AI agentsAPI
Fields · this week
All fields2656Evals327Multimodal286Agents231Frontier LLMs218Recursive self improvement189Inference & serving139Computer vision133Agents & indirect prompt injection132Training & fine-tuning118Robotics115Neural operators114Clinical reasoning110Forecasting time75Code models60Linear bandits56All 32 fields

Open problems across fields

  • Comprehensive and reliable benchmarking for AI capabilities3 papers raise it · 3 address it

    Current benchmarks often lack the depth to fully characterize model capabilities, especially for complex, real-world, or long-horizon tasks.

    • SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Modelsraises · addresses
    • Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimizationraises · addresses
    • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
  • Effective AI agents in complex, dynamic real-world environments3 papers raise it · 3 address it

    AI agents struggle with real-world tasks requiring adaptation, learning from limited data, or debugging live systems, limiting practical deployment.

    • Where LLM Agents Get Stuck Debugging Databases: Access More Than Reasoningraises
    • World In-Context Learning for Agentic Robot Manipulationraises · addresses
    • Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimizationraises · addresses
    • Sage-Taiyi: A Metacognitive Architecture for Scientific Discoveryaddresses
  • Efficient and scalable generation of complex data2 papers raise it · 2 address it

    Generating high-quality, complex data like streaming video or diverse tabular data efficiently and with fewer computational resources is crucial.

    • Few-Step Streaming Video Generation via Condition Shiftingraises · addresses
    • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
  • Unified models for diverse data modalities and tasks2 papers raise it · 2 address it

    Creating single models that handle diverse tasks or data variations within a complex domain reduces complexity and improves generalization.

    • Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Modelraises · addresses
    • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
  • Reducing computational cost of language model attribution1 paper raises it · 1 addresses it

    Understanding how prompt parts influence language model output is crucial for interpretability, but direct methods are computationally expensive.

    • Sketching Language Models for Context Attributionraises · addresses

Named by an AI from these papers' abstracts.

Rising research topics

  • Spiking neural networks11+175.0%
  • Quantum machine learning34+25.9%
  • Character recognition OCR44+25.7%
  • Speech emotion23+21.1%
  • Voice AI76+13.4%
  • Forecasting time133−2.9%
  • Robotics195−3.0%
  • Channel state information18−5.3%

Papers

  • arXiv cs.CVSep 21

    LatentReRig: An SDF-Based VAE with Dual Decoders for Latent-Space Deformation Conditioning

    Daniele Dolci, Fabrizio Poggioni, Carlo Melchiorri

    Transferring deformation between characters with different geometry and topology is challenging because conventional rigs encode behaviour through character-specific structures and correspondences. We present LatentReRig, an experimental framework that investigates whether pose-associated changes can instead be represented as reusable directions in a learned geometric latent space. An SDF-based variational autoencoder is coupled with two decoders: one reconstructs the implicit field, while the other predicts target vertex positions from source geometry and latent deformation conditioning. The source geometry may be neutral or already deformed. Experiments on a controlled humanoid dataset show that several poses induce coherent latent directions across identities, particularly for broad articulated motions. These signals can guide deformation of unseen characters, but explicit predictions remain less accurate for localized changes and corrective contributions. Diagnostic comparisons with repeated SDF sampling show that inter-identity distances exceed same-geometry resampling variability on average, while pose signals exhibit different margins above this baseline. The results…

    PDF
  • arXiv cs.LGSep 21

    PermuFormer: Multi-Task Pretraining for Permutation Representation in Algebraic Combinatorics

    Henry Kvinge

    Diverse pretraining has been shown to be an effective method for learning reusable, domain-aware representations that provide a starting point for fine-tuning on downstream tasks. While much of the excitement in AI for math has been concentrated in the use of frontier reasoning models to solve well-specified problems through the medium of language, narrow, specialized models remain an important component of the AI for math ecosystem. In contrast to large language models, specialized models are usually trained directly on the mathematical objects themselves (e.g., graphs, sequences of numbers) rather than the textual descriptions that characterize these objects. However, the common practice of training specialists from scratch may limit their ability to develop domain-aware representations that capture the multifaceted nature of mathematics. In this paper, we describe an approach to pretraining for permutation-focused tasks in algebraic combinatorics. We introduce PermuFormer, an autoregressive transformer trained on a 2.8 billion token multi-task, multi-encoding corpus. We show that PermuFormer is an effective starting point for fine-tuning on basic tasks unseen during…

    PDF
  • arXiv cs.LGSep 21

    Lightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems

    Sanjay Surendranath Girija, Aniruddh Nath, Li Wei, Yanhao Jiang, Shawn Andrews +4

    Modern production-scale recommender systems rely on complex, multi-task ranking models. Introducing new prediction tasks into these massive systems often causes bottlenecks - it risks negative task conflicts with existing tasks, and can lead to long development and experimentation cycles due to the expensive retraining of backbone models and downstream models or tuning of reward combination formulas. To address the critical challenge of slow experimentation velocity, we introduce the Lightweight Ranking Heads (Light Heads) framework. Designed for continuous online learning environments, Light Heads enable the dynamic injection of new tasks into existing multi-task ranking models, effectively obviating the need for model cold-starting and retraining of backbone models. By utilizing stop-gradients and stateless daily training, this design strictly isolates new tasks, mitigating the risk of adverse task conflicts. Crucially, this framework uses a centralized configuration that allows Light Heads to be added to multiple models simultaneously, unblocking faster training data generation and co-training of downstream models. Successfully deployed at YouTube scale, this approach reduces…

    PDF
  • arXiv cs.LGSep 21

    Predictive Uncertainty for Neural CAE Surrogates

    Kaustubh Tangsali, Mohammad Amin Nabian, Kelvin Lee, Carmelo Gonzales, Sanjay Choudhry

    Neural surrogates can substantially accelerate computer-aided engineering (CAE) workflows, but their use in design requires uncertainty estimates that remain meaningful across varying geometries, spatial prediction fields, and engineering quantities of interest. We investigate how established uncertainty quantification (UQ) approaches behave when adapted to geometry-conditioned neural surrogates. We compare one closed-form and two sampling-based approaches-a Gaussian process (GP)-based method, concrete Monte Carlo (MC) dropout, and deep ensembles-and evaluate them on three large, industry-relevant CAE datasets for external aerodynamics and crash dynamics. We examine whether predicted uncertainties have credible magnitudes, identify locations with larger prediction errors, respond to unfamiliar inputs, and remain informative for derived engineering quantities. On the DrivAerStar dataset, where all three methods are compared, each generally assigns higher uncertainty to locations with larger prediction errors, and validation-based rescaling brings interval coverage close to nominal on a disjoint in-distribution test set. Results on AirFRANS and automotive crash also show useful…

    PDF
  • arXiv cs.CVSep 21

    Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains

    Mahmoud Saeedi Kelishami

    In this paper, we introduce the Directional Total Variation-Regularized Implicit Neural Representation (DTV-INR), an advanced variational paradigm that synergistically integrates coordinate-driven implicit neural networks with an anisotropic, structure-tensor-informed total variation regularizer tailored for resolution-agnostic image super-resolution. Casting the continuous-to-discrete acquisition process into an ill-posed inverse problem framework, our formulation equips a SIREN-architected coordinate network with a dynamic Riemannian metric tensor field D(x). By leveraging its spectral decomposition, the proposed regularizer preferentially directs diffusion parallel to dominant structural contours while penalizing cross-edge dissipation, successfully circumventing the classical staircasing artifacts inherent to scalar total variation schemes. We rigorously prove the well-posedness of this formulation in H^1(Omega) by establishing the existence, uniqueness, and metric stability of the variational minimizer, and realize this via an alternating projected optimization algorithm that decouples network parameter tuning from adaptive tensor field updates. Comprehensive experiments…

    PDF
  • arXiv cs.CLSep 21

    CrisisFake: Benchmark Validity of AI-Generated Text Detection for Disaster Social Sensing

    Xiaoshan Zhou, Zaifu Zhan

    Disaster social sensing converts public social-media posts into evidence for situational awareness and humanitarian response, but plausible LLM-generated posts can contaminate this information stream and distort assessments of needs, damage, and resource priorities. This study empirically investigates whether text-based detectors can distinguish human-authored from LLM-generated disaster posts and what textual cues underlie their judgments. We construct CrisisFake, a Qwen2.5-7B-based dataset of 12,000 texts organized into 3,000 matched semantic units from nine disasters. Each unit contains an original human post, a minimally LLM-proofread human post, a fact-preserving LLM-generated post produced using LoRA, and an affectively reframed version of the artificial post. A separate 6,000-text corpus spanning 42 disaster events is independently constructed to support model selection and threshold calibration. We evaluate OSM-Det, Fast-DetectGPT, Binoculars, and direct LLM judges across five model families, and further examine how disaster-domain calibration and superficial linguistic cues, such as retweet markers, user mentions, hashtags, URLs, punctuation, and text length, affect…

    PDF
  • arXiv cs.PLAgentsSep 21

    Beyond Natural Language: An Agent-Native Language for Autonomous Science

    Yifeng He, Jiachen Liu

    As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relies on natural-language prose: an informal medium prone to ambiguity, hidden assumptions, and untracked limitations that machines cannot reliably audit. We introduce Lara, a machine-checkable language and protocol for checking and revising support for research claims. By turning research arguments into executable artifacts, Lara provides an epistemic kernel for autonomous science: it enables automated validation pipelines for research agents, lets declared bridges connect arguments across papers into an auditable network, and allows both humans and machines to recheck the standing of an encoded claim in milliseconds. In a Lara program, authors explicitly declare their claims, supporting evidence and assumptions, and known objections or limitations. A lightweight, deterministic checker adjudicates these interactions, assigning each claim a reproducible status: "justified", "defeated", "contested", or "gap", which marks a claim whose support is incomplete and locates the unanswered question. Case studies cover…

    AI70PDF
  • arXiv eess.ASVoice AISep 21

    Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesis

    Biel Tura Vecino, Yoach Lacombe, Julian Weber, Zbigniew Łatka, Haitong Zhang +2

    Classifier-free Guidance (CFG) is widely adopted in text-to-speech (TTS) systems to enhance generation quality and conditioning fidelity by interpolating between conditioned and unconditioned predictions. A common unconditional technique is to use an empty representation, in the form of a fixed null vector. In this work, we propose replacing this representation with a learnable unconditional embedding, optimized to represent a meaningful unconditional state. Objective and subjective evaluations demonstrate that learnable null embeddings consistently outperform fixed null embeddings across speaker similarity, speech stability, and expressiveness, while exhibiting greater robustness to larger guidance scales. We further show that learning a distinct unconditional embedding for each of the TTS conditioning modalities allows fine-grained control over speaker and text guidance, showcasing the trade-off between similarity and quality, and stability and expressiveness in the generated speech.

    AI70PDF
  • arXiv cs.AIEvalsSep 21

    From Offline Proxies to Online Decisions: A Layered Engagement Evaluation Framework for Conversational AI

    Xuanyi Li, Vaskar Nath, Hossein Amirkhani, Jay Li, Alex Deng

    Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tested. We ask whether an offline signal designed to be computable without treatment-arm user exposure agrees with the outcomes of those experiments. We contribute a reusable construction and diagnosis checklist that treats an offline proxy as a chain of three alignments: behavioral label to product outcome, learned classifier to candidate-assistant behavior, and aggregated offline signal to experiment effect. A companion evaluation protocol audits the whole composite by interval-aware decision agreement, which compares offline and online confidence intervals instead of point estimates, and by within-experiment ranking. The instantiation we evaluate comprises a fixed evaluation suite on which candidate behavior is scored, an engagement classifier trained to predict session/prompt level engagements, and a calibration layer mapping sample-level score differences to online model-level engagement deltas. We then report the audit: 489 paired offline-online contrasts (one candidate arm against its control) from 27 experiments on a deployed…

    AI60PDF
  • arXiv cs.AIInference & servingSep 21

    Efficient Iterative Retrieval with Heterogeneous Batching

    Dohyun Park, Hubertus Franke, Daniel G. Waddington, Swaminathan Sundararaman, Yongjoo Park

    Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suffer from low throughput and poor GPU utilization because they execute these models in isolation. Coarse-grained partitioning, such as dedicating GPUs to specific tasks, fails to adapt to dynamic workloads and creates computational "bubbles". To address these, we present Orthrus, a serving system that performs heterogeneous batching within a unified inference loop. The primary challenge lies in unifying embedding and generation workloads with conflicting computational patterns while optimizing batch composition for high performance. Orthrus addresses these challenges through chunked embedding with incremental pooling and by adjusting batch composition in a workload-aware manner. Evaluation on four A100 GPUs shows that, relative to baseline deployments, Orthrus achieves 1.28$\times$--4.52$\times$ higher throughput on controlled workloads and up to 55.8% lower end-to-end p99 latency on an iterative-RAG benchmark. We release our code at https://github.com/illinoisdata/Orthrus .

    AIRAG80PDF
  • arXiv cs.AISep 21

    Robust Failure, Conservative Repair: Textual Knowledge Distillation from Cross-Model Failures

    Andrew Ren, Haokun Liu, Chenhao Tan

    Failure-based textual knowledge distillation aims to discover gaps in a model's knowledge by examining its task errors. The distilled knowledge can be useful for the reasoning of both this model ("source model") and other models. However, this transfer of knowledge may not be stable. We define a rule atom to be a standalone rule injected into a model's textual input at inference time. A rule atom can encode transferable task knowledge or model-specific reasoning patches that can confuse other models. Also, the injected rule atoms can be misapplied to unrelated cases, causing the model to incorrectly flip its answer based on irrelevant information. Building on a pipeline that distills training examples into task-specific cheat sheets that aid model reasoning, we examine when failure-derived rules can improve these cheat sheets. Our early experiment shows rule distillation from a single model's failures underperforms the baseline cheat sheet on non-source model families. This motivates Robust Failure, Conservative Repair (RFCR), a textual distillation procedure that derives rules from failures shared across models, sharpens their application boundaries using boundary cases, and…

    PDF
  • arXiv cs.LGSep 21

    Deep Reinforcement Learning on Item-Compatibility Graphs for One-Dimensional Bin Packing

    M. Aslı Aydın

    The one-dimensional bin packing problem (1D-BPP) is a classical NP-hard combinatorial optimization problem with applications ranging from logistics and manufacturing to cloud resource management. Although deep reinforcement learning (DRL) has become a competitive paradigm for data-driven optimization, most learned packing methods target 2D and 3D variants, and intelligent learned solvers for 1D-BPP remain scarce. In this paper, we present a novel end-to-end, size-agnostic graph reinforcement learning framework for 1D-BPP. We formulate the packing process as a Markov decision process on an item-compatibility graph, serving as a structural knowledge representation in which every action merges two partial bins that fit together. A graph neural network actor-critic policy extracts relational features from this representation and is trained through reinforcement learning and decoded by stochastic beam search, enabling a single trained model to generalize zero-shot to instances of any size. We conduct a systematic empirical study across graph encoders, DRL algorithms, reward functions, training distributions, and hyperparameters. Evaluated zero-shot on the full BPPLIB benchmark against…

    AI20PDF
  • arXiv cs.CLAgentsSep 21

    Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development

    Haocheng Xia, Eugene Wu, Yongjoo Park

    Parallel coding agents can produce patches that work alone but fail when merged. This happens when one agent changes an interface or rule that another agent still relies on. We study these failures with stale, a benchmark for semantic coordination. Our evaluation runs the same tests on each patch alone and on their combination, counting only failures introduced by combining the patches. We use three tiers: synthetic tasks with controlled interface changes, pairs of merged pull requests, and constructed tasks that use real Django helpers. Among 834 runs on 417 mined Django pairs, only one showed interference after correcting the grading procedure. On constructed tasks using 12 Django helpers, interference occurred in 97% of runs. A message describing the completed concurrent change recovered 82% of runs. Reviewed pull requests may contain few unresolved parallel changes, even when agents fail on controlled tasks using real code. The constructed failure rates do not estimate how often these problems occur in practice.

    AIEvals80PDF
  • arXiv stat.MLSep 21

    PICPIs: Prediction-Interval-Conditional Prediction Intervals

    Xuelin Yang, Baihe Huang, Yilong Hou, Guido Imbens, Michael I. Jordan

    A classical question in statistics is which observable quantities to condition on when drawing inferences about unobservable targets. For conformal prediction in nonparametric uncertainty quantification, standard marginal validity offers limited resolution at the prediction values on which decisions are based, and fully conditional guarantees with respect to the covariates are provably unattainable. We address this gap by introducing a prediction-based conditioning framework that we refer to as Prediction-Interval-Conditional Prediction Intervals (PICPIs). Formally, a PICPI is an interval $I$ satisfying a self-consistency condition: $$\mathbb{E} [Y \mid p(X) \in I] \in I,$$ for predictive model $p$, contextual covariate $X$, and outcome $Y$. Thus, an interval simultaneously defines a stratum of prediction values and certifies that the mean outcome in that stratum lies in the same interval. This self-consistency condition yields data-adaptive strata without altering the original prediction. Such intervals can be constructed using practical algorithms. Under regularity of the prediction distribution, the constructed intervals cover all but an arbitrarily small fraction of…

    PDF
  • arXiv cs.CVSep 21

    Sex Estimation from Footwear Outsole Impressions Using CNN Transfer Learning and Interpretable Image Statistics

    Jinyi Niu, Ziyi Song, Weining Shen

    Footwear outsole impressions are a common form of forensic pattern evidence, yet quantitative methods for estimating wearer attributes from these images remain relatively underdeveloped. We investigate binary sex estimation from footwear outsole impressions by comparing convolutional neural network (CNN) transfer learning with traditional feature-based classification. Using a publicly available outsole-impression dataset, we adopt a shoe-level training and test partition that keeps replicate scans of the same physical shoe together to reduce data leakage. We evaluate pretrained CNNs through end-to-end fine-tuning, frozen feature extraction followed by support vector machine classification, and hybrid feature fusion incorporating handcrafted, geometric, and metadata-derived descriptors. Fine-tuned CNNs achieve the strongest overall predictive performance and substantially outperform traditional classifiers trained on the manually specified descriptors alone, while frozen-feature approaches offer a less computationally demanding alternative. Exploratory analysis of low-dimensional CNN representations reveals associations with frequency threshold ratio, image contrast, and…

    PDF
  • arXiv stat.MLSep 21

    Penalized Nonreversible Langevin for Constrained Sampling

    Pervez Ali, Weihao Dong, Xiaoyu Wang

    We propose penalized nonreversible Langevin algorithms for sampling from $π(x)\propto e^{-f(x)}\mathbf 1_{\mathcal C}(x)$, where $\mathcal C\subset\mathbb R^d$ is a compact convex set. The algorithms combine a squared distance penalty with constant or compatible state dependent skew symmetric perturbations that preserve the penalized Gibbs distribution. For smooth, possibly nonconvex $f$, we derive nonasymptotic total variation bounds for the full gradient algorithm under a log Sobolev inequality. When unbiased stochastic gradients are available, we establish $2$-Wasserstein bounds under global contraction and Lipschitz conditions on the full drift in an adapted quadratic metric. For a fixed penalty parameter, the error relative to the penalized Gibbs distribution decays exponentially to an $\mathcal{O}(\sqrtη)$ neighborhood, where $η$ is the stepsize. We also bound the discrepancy between the penalized Gibbs distribution and the constrained target. In a two dimensional quadratic model, we establish nonreversible acceleration by tuning the skew perturbation to the curvature imbalance induced by penalization. With the target accuracy and smaller curvature fixed and initial…

    PDF
  • arXiv cs.ROSep 21

    VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models

    Jiuyi Xu, Qing Jin, Meida Chen, Song Wang, Yang Sui +1

    Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer scope, numerical format, and calibration. We introduce \textbf{VLAQuantBench}, a controlled evaluation with 409 runs and 94,574 simulation episodes: four models on LIBERO, with X-VLA additionally evaluated on three simulation benchmark families. Under uncalibrated W4A4 round-to-nearest quantization, expanding a $π_{0.5}$ action-head subset from 126 to 167 layers raises success from 7.0\% to 70.5\%. Fixed-observation replay confirms a corresponding numerical recovery. Two-episode calibration removes the severe joint failures in the tested subsets, whereas the same smoothing-and-clipping recipe lowers $π_0$ success and does not recover OpenVLA-OFT end-to-end. For OpenVLA-OFT, protecting one 28,672-parameter output projection instead restores near-baseline success: the remaining 441 eligible linear layers retain W3 on LIBERO-Long or eight-bit activations across all four suites. Task-clustered intervals support the large failure and recovery contrasts. These results establish recipe-dependent interactions and…

    PDF
  • arXiv cs.ROSep 21

    PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration

    Abolfazl Babanazari, Carson Cramer, Tyler Summers, Carlos Nieto, Kaveh Fathian

    Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by outliers. Planar regions are particularly difficult for conventional point descriptors and are therefore often suppressed or discarded before matching. We present PARTE (Plane-Assisted Robust Transformation Estimation), a global registration method that instead treats planar structure as complementary registration evidence. PARTE extracts planar patches and represents them using our novel Plane Context Histogram (PCH), a descriptor that encodes the geometry surrounding each patch, while a two-level matching procedure identifies reliable plane correspondences. Candidate point and plane correspondences are combined in a confidence-weighted compatibility graph for joint outlier rejection, followed by rigid transformation estimation. When no usable plane correspondences are available, PARTE naturally reduces to point-only registration. We evaluate PARTE on 8,097 registration pairs across six indoor and outdoor benchmarks spanning dense RGB-D and sparse LiDAR measurements. Evaluations show PARTE achieves the highest overall success…

    PDF
  • arXiv cs.LGSep 21

    Extending FunctionGemma for Practical On-Device Mobile Function Calling

    Ali Rezagholizadeh, Soheila Samiee

    On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or narrow mobile-action catalogs. We extend FunctionGemma 270M-it to practical Android workflows by introducing MOBILEACTIONSEXTENDED, a synthetic, schema-validated dataset of ~9,500 conversations covering fifteen device-control categories, including messaging, phone calls, camera/screenshot, brightness control, device-status queries, flashlight control, and application management. We fine-tune the 270M model with TRL supervised fine-tuning under completion-only loss, producing an extended specialist and a combined model trained jointly with Google's MOBILEACTIONSGOOGLE. On MOBILEACTIONSEXTENDED, end-to-end accuracy improves from 29.3% for the base model and 17.2% for Google's Mobile-Actions variant to 76.5%. The combined model retains 76.5% on MOBILEACTIONSEXTENDED and reaches 82.3% on MOBILEACTIONSGOOGLE, down from the 90.3% of Google's Mobile-Actions specialist, representing an 8.0-percentage-point trade-off in return for doubling category coverage. We release the dataset, fine-tuned models, reproducible training/evaluation pipeline,…

    PDF
  • arXiv cs.AISep 21

    From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought

    Renee Jia, Di Mu

    Chain-of-thought (CoT) monitoring is only meaningful if written reasoning causally constrains the answer. We introduce continuation-based causal testing, an ablation-patch intervention that perturbs one reasoning step, truncates the chain, and forces the model to continue from the corrupted prefix. It measures how load-bearing a CoT is for the final answer, a behavioral notion distinct from mechanistic faithfulness. Across Gemma-2-9B-IT, Llama-3.1-8B-Instruct, and DeepSeek-R1-Distill-Qwen-7B on GSM8K, MMLU, and BIG-Bench Hard, CoT load-bearingness tracks model-relative task difficulty: on easy tasks models silently bypass their own reasoning; on hard tasks they follow corrupted steps and propagate errors. A matched 2x2 analysis shows task difficulty dominates perturbation type: error propagation rises 16x from GSM8K to BBH multistep arithmetic, and a variance partition over 28,584 continuations attributes 98.8% of explained deviance to task difficulty versus 0.8% to perturbation type. Reasoning-specific RL suppresses error propagation and compresses the gradient. A four-variant judge-sensitivity analysis and blind two-annotator study (n=500) show the error-propagation vs.…

    PDF
Load more