Irreversibility

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 20

Sep 30, 2026cs.AI

Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets

Evaluating interactive agents is expensive. Agent behavior is stochastic, so reliability must be measured over repeated trials, but failures are rare and differ widely in how much they matter. Standard benchmarks spend this budget uniformly: a read-only lookup is sampled as often as an irreversible payment action. We instead formulate evaluation as a sequential allocation problem. Given a fixed trial budget and a set of scenarios whose failure behavior is unknown, which scenarios should be run, and run again? We propose a risk-aware contextual Thompson Sampling policy that combines a pre-execution scenario context vector and a fixed impact score with the failure outcomes observed during evaluation, and we test it by offline replay over 70

τ

-bench airline scenarios and 824 recorded trials. Our main result is at the smallest budget: with only 50 trials (

6\%

of the corpus), the policy recovers

86\%

of the impact-weighted failures an oracle could find, compared to

25\%

for uniform allocation. It discovers

3.5\times

more impact-weighted failures (215.4 vs. 62.2) with the same number of trials, delivers

5\times

the discovery per dollar, and cuts the budget wasted on scenarios that never fail from

34\%

to

2.8\%

. The rest of our analysis demonstrates and qualifies this result: a budget sweep shows the advantage shrinks as the budget approaches the corpus size, and paired significance tests show that scenario context helps mainly at small budgets while posterior-based exploration helps at moderate ones. Risk-aware adaptive allocation therefore helps most exactly where evaluation budget is scarcest.

Priyanath Maji, Spandan Ghose Chowdhury

Georgia Institute of Technology Atlanta, GA 30332

Thompson Sampling Token Budget Allocation Sequential Decision Making Irreversibility

Sep 14, 2026cs.LG

Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative

Outliers are important for stress-testing algorithms and understanding system behaviour under rare conditions. Despite being commonly described as low-likelihood events, existing generative approaches rarely control likelihood explicitly. In this work, we introduce a measure-theoretic notion of outliers based on the distribution of log-likelihood values, which is guaranteed to assign higher probability mass to low-likelihood events with a specifiable magnitude. Building on this formulation, we derive how likelihood reweighting modifies the diffusion score and use this relation to motivate a controlled modification of the reverse-time dynamics. In particular, likelihood reweighting implies a scaling of the score function with a control term derived from the Radon-Nikodym derivative of the likelihood distributions. Correspondingly, the updated score function can be obtained with no retraining of the diffusion model. We exploit the Ornstein-Uhlenbeck semigroup underlying diffusion models to motivate an exponentially interpolated controller which approximates the true control. Experiments demonstrate controlled generation of low-likelihood samples while remaining consistent with the data geometry.

Amartya Mukherjee, Tristan Milne, Kry Yik-Chau Lui +2

Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario, Canada N2L 3G1 · Royal Bank of Canada, 1 Place Ville Marie, Montreal, Quebec, H3C 3A9

Score-Based Diffusion Model Outliers Uncertainty Score Generative Models Implicit Differentiation Irreversibility+1

Sep 7, 2026q-bio.GN

Human mutation field reveals an equilibrium-like structure with irreversible circulation

The evolution of DNA sequences can be viewed as stochastic dynamics on a high-dimensional discrete space, but it is unclear when empirical transition biases reduce to an effective energy landscape versus retain irreducible non-equilibrium circulation. Human context-dependent mutation probabilities offer a direct test: every single-nucleotide substitution in a local context has a reverse substitution, so the logarithm of the forward-to-reverse probability ratio defines an antisymmetric field-the human mutation field. We show this field has a dominant gradient component and a smaller but reproducible curl component. Using seven-base human germline substitution probabilities, we infer an effective mutational landscape with a Siamese neural network constrained to predict only energy differences. This model predicts forward-to-reverse log-ratios for held-out mutations with a correlation of about 0.93, close to both an unconstrained predictive reference (0.948) and the empirical reversible ceiling from Hodge projection (about 0.96). Although trained only on mutation probabilities, the inferred landscape largely recovers short-word genomic composition and Chargaff reverse-complement symmetry for sequences up to length four. Deviations from equilibrium structure reveal a small but detectable nonequilibrium component: a residual irreversible circulation violating the Kolmogorov cycle condition for detailed balance, reproducible across African, Asian, and European populations, and strongest in CpG-linked cycles and CpG-transition edges, consistent with methylcytosine deamination. These results give a thermodynamic decomposition of the human mutation field: most mutation bias is organized by a local equilibrium-like energy landscape aligned with genome composition, while the residual circulation points to specific directional mutational mechanisms.

Isabella Caranzano, Daniel Maria Busiello, Stefano Priorelli +2

AI and Computational Biomedicine Unit, Department of Medical Sciences, University of Torino, Torino, Italy · Department of Physics, University of Padova, Padova, Italy · Max Planck Institute for the Physics of Complex Systems, Dresden, Germany

Lattice Mutation Free-Energy Landscape Genome-Wide Association Study Irreversibility Equilibrium Symmetry+1

Aug 31, 2026cs.AI

The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems

Fleets of LLM agents now externalize effects that cannot be fully undone: they move money, deploy code, delete data, and disclose information. Current controls check one effect at a time, so a fleet of individually authorized agents can overdraw its principal's risk under a shared trigger while every local gate stays correct. We propose the irreversibility budget, a cumulative account of residual value-at-risk that a trusted runtime maintains for each principal across agents, workflows, and tenants. Treating irreversibility as a first-class resource, the runtime charges each effect its residual loss below the agent and denies the marginal effect once the aggregate would overdraw the budget. Getting the price right is hard, because effects are heterogeneous, adversarially declared, and correlated. We perform a controlled study in which per-effect gates admit fleet-level overdraws of up to 48 times the tenant's risk limit while the budget holds every correctly charged run within that limit. Conservative, dependency-aware pricing remains the central open problem for a deployable design.

Bardia Mohammadi, Laurent Bindschaedler

Max Planck Institute for Software Systems Saarbrücken, Germany

Runtime Safety Filtering Agentic Deployments Irreversibility Artificial Intelligence Risk Conditional-Value-At-Risk Admissibility+1

Aug 5, 2026cs.AI

WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models

Interactive video world models are essential for long-horizon planning and exploration, yet they suffer from compounding errors. Post-training methods such as reinforcement learning (RL) can improve these models, but they hit a verification bottleneck: for arbitrary action sequences, no ground-truth future state exists to measure long-term drift. Our key insight is that reversible action cycles make this verification possible: a sequence composed with its inverse must analytically return to the initial state, yielding annotation-free supervision on long-horizon correctness. Building on this, we introduce WorldCycle, a self-verifiable RL framework that constructs closed action cycles and their repeated executions from ordinary action sequences, and optimizes two complementary rewards: a spatial closure reward enforcing symmetry between mirrored forward and reverse segments, and a temporal consistency reward aligning states across repeated cycle executions. These rewards force the model to learn actions as consistent state operators rather than memorized temporal patterns, and extend naturally to out-of-distribution composite action cycles that the base model handles poorly. We further release CycleBench, a diagnostic benchmark for state-returning ability under complex action structures. WorldCycle reduces state returning drift by up to 44% and lifts composite-action accuracy nearly 4x over the base model, providing a vital foundation for physically grounded world models.

Bohai Gu, Yueyang Yuan, Taiyi Wu +9

1The Hong Kong University of Science and Technology · 2Wuhan University · 3AI Technology Center, Tencent Video, Tencent

Video World Models Long-Horizon Inference Reinforcement Learning With Verifiable Reward Irreversibility Bivariate Bicycle Codes

Aug 1, 2026cs.CV

Diagnosing Under-Development of Irreversible Processes in Video Generation

Many physical attributes are \emph{irreversible}: ice melts but does not re-freeze, paper chars but does not un-burn. Do video generators respect this? We show the question is hard to measure, and that what can be measured reliably is \emph{development} rather than reversal. Metrics of local reversal are null-degenerate: a per-clip violation rate scores

0.50

on pure noise, and a variance-normalized reversal residual sits at its noise ceiling. What survives null-testing is a two-part protocol: progress (a directional attribute correlation) and a stasis rate. Under this protocol, generated video separates cleanly from real footage, and the gap is human-validated. Across seven text-to-video models, real reference footage advances (

ρ{=}{+}0.40

,

35\%

static) while every generator shows near-zero progress and

92

--

100\%

stasis; nine annotators rate real footage far above generated (

2.75

vs.\

0.99

on a

0

--

4

scale). The reliable finding is \emph{under-development}: generators barely advance irreversible attributes rather than reversing them. As a complementary mechanism, we show that post-hoc readout guidance is gameable, whereas enforcing monotonicity by construction in a disentangled attribute latent removes the gameable readout, validated in controlled and semi-synthetic settings.

Jian Xu, Yanning Wu, Delu Zeng +2

Video Generation Irreversibility Violation

Jul 28, 2026cs.MA

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective can be fragmented into locally plausible subtasks, allowing malicious intent to evade detection by any single agent. This is a growing social-impact challenge: systems handling sensitive information or consequential tools can turn routine delegation into unauthorized disclosure or unsafe action. We argue that this failure mode is better understood as a semantic information-flow problem than as a single-turn prompt classification task. To address this, we propose SafeFlow, a defense framework for multi-agent systems that formalizes malicious cross-agent propagation as a semantic information-flow problem. SafeFlow attaches structured semantic taints to root requests, propagates them through a dynamic collaboration graph, and performs workflow-level validation to reconstruct the global risk context before irreversible actions are committed. Evaluated on four benchmarks spanning prompt injection, jailbreak-based unsafe tool use, risky code execution, and harmful web-agent behavior, SafeFlow reduces attack success rates compared to undefended baselines and external defenses while retaining high benign task completion and a high paired safe--harm success rate. Our findings show that multi-agent systems still lack mechanisms for preserving risk semantics across delegation boundaries. This gap can turn routine delegation into privacy harms or unsafe actions that affect people and organizations. SafeFlow keeps this risk visible throughout the workflow, before it results in harm.

Haowen Dai, Zonghao Ying, Wenfeng Li +10

University of Nottingham Ningbo China · Beihang University · Shandong University +6

Information-Flow Control Malicious Agents LLM Defense Mechanisms Safer Irreversibility

Jul 17, 2026cs.CV

Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

Diffusion-based methods have achieved impressive performance in real-world image super-resolution (Real-ISR) by leveraging large pre-trained stable diffusion (SD) models as powerful generative priors. However, these methods still face two key limitations. First, existing SD-based one-step and multi-step Real-ISR approaches adopt a unified processing paradigm for all input samples, ignoring the varying restoration difficulty across images. Second, the aggressive resolution reduction of the VAE in SD models (e.g., 8x downsampling) leads to irreversible loss of fine-scale details, which cannot be recovered by the subsequent diffusion process. To address these limitations, we propose a Difficulty-aware Dynamic Routing (DDR) strategy that overcomes the rigid, one-size-fits-all processing paradigm. Specifically, we first design a difficulty estimator to predict the restoration cost of each input image, enabling automatic assignment to a network of appropriate capacity. Then, we construct a set of Real-ISR networks with varying model capacities by modulating the spatial downsampling ratio of the VAE in the SD backbone, thereby preserving more high-frequency information for challenging cases while maintaining efficiency for simpler inputs. Extensive experiments have demonstrated the superior efficiency and effectiveness of the proposed model compared to recent state-of-the-art methods.

Xue Wu, Kang Zhao, Kafeng Wang +4

Xidian University, Xi’an 710071, Shaanxi, China. · Tsinghua University, Beijing, China.

Real-World Image Super-Resolution Residual Conditional Diffusion Model Irreversibility

Jun 27, 2026cs.LG

A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility

We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories. In the local regime where latent dynamics admit an effective Markovian description, this path measure takes the Onsager-Machlup form. Within this framework, prediction (most probable trajectory), planning (constrained optimization), and uncertainty (fluctuations) emerge as operations on a single action functional. We decompose the latent dynamics into reversible and irreversible components and introduce operational measures of entropy production from model rollouts. In controlled small-scale attention-based models, we find that attention asymmetry is acquired during training in proportion to the irreversibility of the data. Symmetrizing the learned attention suppresses entropy production and selectively degrades long-horizon prediction of irreversible dynamics while preserving relaxational prediction. These results suggest that irreversibility may serve as a computational resource for predictive world models. More generally, the fundamental predictive object is a distribution over future paths rather than states.

Gunn Kim

Department of Physics, Sejong University, Seoul 05006, Republic of Korea

Latent World Models World Models Irreversibility Latent Dynamics Long-Horizon Forecasting Planning

Jun 20, 2026cs.AI

When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR

Reinforcement learning with verifiable rewards (RLVR) is increasingly applied to large vision-language models (LVLMs), yet outcome-only optimization can drive a model to stop attending to the video and instead exploit linguistic priors -- a failure we call a visual shortcut. While the existence of such perception bypass is by now documented, how it forms, whether it can be undone, and when intervention still helps remain open. We treat the strength of a grounding penalty, lambda, as a control knob and characterize the formation-reversal dynamics of visual shortcuts along the training time axis. On a held-out, out-of-distribution diagnostic set, we find: (i) a sharp onset -- shortcut reliance emerges abruptly over a narrow window of optimization steps and is robust across random seeds; (ii) a monotone dose-response -- increasing lambda progressively suppresses the shortcut, and at an intermediate dose the trajectory first forms and then reverses the shortcut, exposing a hysteresis-like asymmetry between acquiring and removing it; and (iii) a critical intervention window -- applying the penalty before onset arrests shortcut formation, whereas the same penalty applied after consolidation is markedly less effective. Together these results recast visual-shortcut collapse not as a binary defect but as a controllable, time-dependent, and asymmetric process, with direct implications for when and how strongly to regularize multimodal RLVR.

Zekun Xu

School of Computer Science, The University of Sydney, Sydney, Australia

Reinforcement Learning With Verifiable Reward Video-Language Models Shortcut Learning Reverse Irreversibility

Jun 1, 2026cs.AI

ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents

Clinical practice is not the selection of an answer from enumerated options: a physician gathers heterogeneous information incrementally and commits to sequential, irreversible decisions under uncertainty. Static benchmarks cannot probe and existing interactive medical benchmarks each compromise on at least one of them. We present ClinEnv, an interactive benchmark that evaluates LLMs as attending physicians over real inpatient admissions under a paradigm we term Longitudinal Inpatient Simulation. Each case is automatically constructed into an ordered sequence of decision stages; at every stage the model must actively query four specialized agents before committing to medications, procedures, and diagnoses. ClinEnv scores both what the model decides, through deterministic ontology-grounded matching, and how it gathers information. Across seven models, the strongest reaches only 0.31 decision F1, and outcome quality is sharply decoupled from process quality. Difficulty concentrates in management decisions and later stages, where models recover discharge diagnoses far more reliably than management actions (0.51 vs. 0.17 F1) and continue to issue redundant queries as cases progress. ClinEnv makes this information-acquisition gap, invisible to outcome-only evaluation, directly measurable.

Yuxing Lu, Yushuhong Lin, Wenqi Shi +4

1Georgia Institute of Technology · 2Peking University · University of Texas Southwestern Medical Center +1

Simulated Patients Electronic Health Records Ontology Irreversibility

May 31, 2026cs.LG

Physics-Informed Deep Learning for Entropy Prediction in Heterogeneous Systems: Thermodynamic and Information-Theoretic Case Studies

Entropy production governs irreversibility and uncertainty in both physical and information-theoretic systems. While Physics-Informed Neural Networks (PINNs) successfully solve differential equations, current architectures remain inherently domain-specific. The extraction of domain-invariant entropy representations across fundamentally different physical laws remains unexplored. This paper introduces a unified Physics-Informed Deep Learning (PIDL) framework that simultaneously enforces differential equation residuals and information-theoretic bounds within a single neural architecture. We demonstrate this framework via two canonical studies: (i) a thermodynamic continuous stirred-tank reactor (CSTR) model solving governing ODEs, where a Softplus constraint strictly enforces the Second Law of Thermodynamics; and (ii) an information-theoretic financial market model solving the inverse Fokker-Planck PDE to infer latent drift and diffusion coefficients, guaranteeing diffusion positivity via a Softplus constraint while naturally inducing Shannon entropy. Three model variants are evaluated: two domain-specific baselines and one shared-encoder architecture. The PIDL framework guarantees absolute thermodynamic admissibility with zero Second-Law violations and exhibits exceptional data efficiency, retaining >90% predictive accuracy using merely 30% of available training data. Furthermore, a post-hoc Ruppeiner Riemannian geometric analysis of the learned entropy surface successfully identifies thermodynamic phase instabilities. This methodology provides a robust, domain-agnostic architecture for physics-constrained entropy modeling, advancing applications in sustainable process design and quantitative financial risk assessment.

Biswajeet Sahoo, Debadutta Patra

Durham University, Durham, UK · Department of Chemical Engineering Veer Surendra Sai University of Technology, Burla, India

Parametric Physics-Informed Neural Network Physics-Informed Learning Information-Theoretic Limits Chemical Process Systems Irreversibility Deep Learning

May 21, 2026cs.AI

Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression

The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when they process long contexts. Current KV Cache eviction has become an important research direction; however, existing methods based on fixed Soft Tokens (e.g., Judge Q) rely on a static parameter set as the query to evaluate the importance of KV pairs, so they cannot adapt dynamically to different input prompts, and they cannot precisely capture complex and changing task relevance. Also, evicted KV pairs are discarded permanently, so this causes irreversible information loss and context breaks. To address this problem, we propose Meta-Soft, a dynamic compression framework based on probe-driven context integration. Specifically, we build a meta-library with a learnable orthogonal basis matrix

\mathcal{L}

, and we use a selector network with Gumbel-Softmax to produce differentiable sparse combination weights, so we dynamically synthesize the most targeted

k

Soft Tokens from the input prompt features. We append these Soft Tokens to the end of the input sequence to probe key information. We also introduce an attention-flow based integration mechanism, which redistributes the semantic information of removed tokens into retained tokens, and this keeps the dropped context information effectively. Experiments on multiple datasets show that our method outperforms existing state-of-the-art eviction methods and provides a new solution for KV Cache compression.

Wei Luo, Yi Huang, Songchen Ma +3

Guangdong Institute of Intelligence Science and Technology · University of Macau · Chinese University of Hong Kong, Shenzhen +1

Key-Value Cache Compression Key-Value Cache Context-Awareness Irreversibility

May 21, 2026cond-mat.stat-mech

Thermodynamic Irreversibility of Training Algorithms

The training algorithms for AI systems all introduce far-from-equilibrium dynamical processes, and understanding the irreversibility of these algorithms is a fundamental step towards understanding the learning dynamics of modern AI systems. In this work, we establish a general framework for defining and analyzing the irreversibility of training algorithms. We show that four different ways to characterize the irreversibility of dynamical processes are equivalent to leading order in the step size

η

: numerical backward error

φ_{\rm DE}

, time-renormalized correction

φ_{\rm TR}

, microscopic time reversal asymmetry

φ_{\rm TA}

, and the (regularized) stochastic-thermodynamic entropy production

φ_{\rm ST}

. The irreversibility gives rise to a time-reversal-symmetry-breaking emergent force that generically breaks non-isometric continuous reparametrization symmetries, preserves orthogonal symmetries, and leads to a universal preference for those learning trajectories that minimize the entropy production rate.

Liu Ziyin, Yuanjie Ren, Adam Levine +1

1Massachusetts Institute of Technology · 2NTT Research

Irreversibility Statistical Physics Thermodynamics Learning Dynamics Multi-Stage Training Symmetry+1

May 5, 2026cs.CV

A Deeper Dive into the Irreversibility of PolyProtect: Making Protected Face Templates Harder to Invert

This work presents a deeper analysis of the "irreversibility" property of PolyProtect, a biometric template protection method initially proposed for securing face embeddings. PolyProtect transforms embeddings into protected templates via multivariate polynomials, whose coefficients and exponents are distinct for each subject enrolled in the face recognition system. A polynomial is applied to consecutive sets of elements from a given embedding, where the amount of overlap between the sets is a tunable parameter. We begin our irreversibility analysis by demonstrating that PolyProtected templates are easier to invert using a numerical solver based on cosine distance, as opposed to Euclidean distance (used in the earlier PolyProtect work). To make this inversion more difficult, we then propose a "key selection algorithm", which tries to choose "keys" (coefficients and exponents of the PolyProtect polynomial) that enhance the irreversibility of PolyProtected templates, compared to when the keys are purely random. Our experiments show that this algorithm is effective at generating PolyProtected templates that are significantly more difficult to invert, and that it approximately equalises the irreversibility of PolyProtected templates generated using different "overlap" parameters. This allows for better control of the irreversibility versus accuracy trade-off, known to exist across different overlaps. We also show that accuracy in the PolyProtected domain can be affected by the range in which the embedding elements lie, but that this can be improved by normalizing the embeddings prior to applying PolyProtect. This work is reproducible using our open-source code.

Vedrana Krivokuća Hahn, Jérémy Maceiras, Sébastien Marcel

All authors are with Idiap Research Institute in Martigny, Switzerland.

Biometrics Inverse Design Irreversibility Polynomials

May 2, 2026cs.AI

AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries

Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks, organizational inertia, and specialized supply chains. By contrast, AI capabilities can be copied, invoked, embedded in workflows, and scaled across institutions at low marginal cost. This paper argues that declining deployment friction changes the safety problem at its root. Safety is not only local output correctness or preference alignment, but the control of irreversibility under rising decision density. The paper formalizes this claim through decision-energy density: the rate-weighted capacity of a node to generate, evaluate, select, and execute consequential decisions. It then identifies three sovereignty boundaries that determine whether AI remains an amplifier within a human-governed system or becomes a de facto control center: irreversible decision authority, physical resource mobilization authority, and self-expansion authority. The model shows how efficiency pressure, path dependence, scale feedback, and weak boundary constraints concentrate decision-energy in the most efficient node. This concentration can diffuse responsibility and raise the probability of irreversible system-level loss even when local per-action error rates remain low. The main result is a boundary stabilization theorem. It shows that safety need not require proving that advanced systems are always correct. Instead, it requires institutional and technical designs that prevent irreversible power from being released by a single high-efficiency node. The paper reframes AI safety as layered control, authorization, and externally reviewable limits, linking alignment, security engineering, organizational economics, and institutional design.

Wesley Shu, Peng Wei

The Institute of Energetic Paradigm · College of Plant Protection Southwest University, China

Artificial Intelligence Safety Authority Artificial Intelligence Systems Irreversibility Boundaries

Apr 25, 2026cs.CL

Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing

While annotated corpora are crucial in the field of natural language processing (NLP), those containing copyrighted material are difficult to exchange among researchers. Yet, such corpora are necessary to fully represent the diversity of data found in the wild in the context of NLP tasks. We tackle this issue by proposing a method to lawfully and publicly share the annotations of copyrighted literary texts. The corpus creator shares the annotations in clear, along with a non-reversible hashed version of the source material. The corpus user must own the source material, and apply the same hash function to their own tokens, in order to match them to the shared annotations. Crucially, our method is robust to reasonable divergences in the version of the copyrighted data owned by the user. As an illustration, we present alignment experiments on different editions of novels. Our results show that our method is able to correctly align 98.7 to 99.79% of tokens depending on the novel, provided the user version is sufficiently close to the corpus creator's version. We publicly release novelshare, a Python implementation of our method.

Arthur Amalvy, Vincent Labatut, Xavier Bost +1

Institute of Information Science, Academia Sinica, Taiwan · Laboratoire Informatique d’Avignon, Avignon Université, France · Aiway, France

Text Corpora Copyright Defenses Authorship Locality-Sensitive Hashing Literature Natural Language Processing+1

Apr 25, 2026cs.LG

Revisable by Design: A Theory of Streaming LLM Agent Execution

Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon completion does the dialogue resume. This forces users into a binary choice: wait for a potentially incorrect output, or interrupt and lose all progress. We reject this assumption and propose the stream paradigm, in which agent execution and user intervention are concurrent, interleaved processes sharing a bidirectional channel. We formalize this paradigm through a reversibility taxonomy that classifies every agent action as Idempotent, Reversible, Compensable, or Irreversible, and arrive at a core conclusion: an agent's flexibility is bounded by its reversibility. We prove that conflicting compensable actions impose unavoidable adaptation costs and that conflicting irreversible actions make full specification satisfaction impossible -- these costs are properties of the action space, not of the algorithm. Guided by this insight, we present the Revision Absorber, a reactive algorithm based on the Earliest-Conflict Rollback rule that is structurally optimal under mild assumptions. Experiments on StreamBench with real LLM agents validate all predictions: the Absorber matches the quality of a brute-force full-restart baseline while wasting an order of magnitude fewer steps of already-completed work, turning mid-execution revisions from a dead-end into a first-class interaction.

Zhiyuan Zhai, Ming Li, Xin Wang

Fudan University · Guangming Lab

Agent Loop Rollback Irreversibility Theory

Apr 21, 2026cs.IT

Watts-per-Intelligence Part II: Algorithmic Catalysis

We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that encoding this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for an algorithmic catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within an information thermodynamic constraint on intelligent computation.

Elija Perrier

Centre for Quantum Software and Information, University of Technology Sydney, Australia.

Thermodynamics Information-Theoretic Limits Tractability Heterogeneous Catalysis Irreversibility General Intelligence+2

Date pendingcs.LG

Safe Learning Under Irreversible Dynamics via Asking for Help

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that this combination enables the agent to learn both safely and effectively. Under standard online learning assumptions, we provide an algorithm whose regret and number of mentor queries are both sublinear in the time horizon for Markov decision processes with irreversible dynamics and infinite state spaces. Our proof involves a sequence of three reductions, making our result more general than a single algorithm. Conceptually, our result may be the first formal proof that it is possible for an agent to obtain high reward while becoming self-sufficient in an unknown, unbounded, and high-stakes environment without resets.

Benjamin Plaut, Juan Liévano-Karim, Hanlin Zhu +1

Division of Computer Science University of California Berkeley, CA 94720-1776, USA

Markov Decision Processes Irreversibility State Space Assistant Tutors