Machine Learning · Cross-listed from cs.SE
From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning
Ankur Garg, Corey Yang-Smith, Rishav Rishav et al. (+2 more)
We introduce C2C (From Codebase to Culprit), a framework for precise bug localization that progressively reduces the debugging search space across multiple levels of granularity: files, functions, and lines of code. To mirror developer's natural top-down debugging workflows, C2C integrates semantic
retrieval and Hierarchical Reinforcement Learning (HRL) in a two-stage process. First, it performs recall-oriented
retrieval of buggy candidates via semantic vector similarity search using bug-report text, including available stack-trace information, against a database of
embeddings, where the
embeddings are fine-tuned via contrastive learning with CodeBERT. Building on this reduced search space, the HRL framework incrementally localizes bugs,
reasoning from files to functions and ultimately to individual lines of code. Unlike prior approaches which operate at a single granularity, C2C enables multi-resolution localization while maintaining contextual consistency across decisions. Experiments on real-world Java and Python
datasets demonstrate that C2C improves
retrieval precision and localization accuracy. Ablation studies further highlight the contributions of hierarchical decomposition, structured learning signals, and reward shaping in advancing multi-level bug localization.
Read the full abstract ▾
All authors Ankur Garg, Corey Yang-Smith, Rishav Rishav, Ahmad Abdellatif, Samira Ebrahimi Kahou
Machine Learning · Cross-listed from cs.RO
GestAdapt: Workspace-Conditioned Co-Speech Gesture Generation for Humanoid Robots
Bosong Ding, Xianglin Zhang, Miao Xin et al. (+2 more)
Co-
speech gestures for
robots must adapt not only to
speech and embodiment, but also to the workspace available for performing the motion. Since the same
speech can be accompanied by different gestures, a
robot can respond to workspace constraints, e.g., gestures for
speech next to a wall. In these scenarios, the
robot should gesture in a suitable motion rather than simply correcting an unconstrained one. To achieve this goal, we present GestAdapt, a workspace-conditioned framework that conditions co-
speech gesture generation on a prescribed wrist workspace. The GestAdapt framework learns from six complementary co-
speech corpora through a shared motion representation and supports retargeting to different
robot embodiments. Quantitative evaluation shows that generated motions remain close to the real-motion distribution while respecting the workspace. In a user study, gestures generated under modified workspace constraints receive a mean quality score of 3.24/5, above our no-workspace variant (2.43/5) and below the reference motions (3.68/5). In a real
robot evaluation, all compared motions are retargeted to the Reachy2 humanoid
robot under identical workspace constraints. Motions generated with our framework rank first in 69.7% of comparisons, higher than our no-workspace variant baseline and retargeted ground-truth motions constrained afterward. Overall, the results support adapting gestures to the available workspace during generation, rather than modifying unconstrained trajectories afterward to satisfy workspace constraints, potentially compromising gesture naturalness.
Read the full abstract ▾
All authors Bosong Ding, Xianglin Zhang, Miao Xin, Murat Kirtay, Giacomo Spigler
Machine Learning · Cross-listed from math.OC
Unified Optimality Conditions for Stochastic Optimal Control in the Rough Path and Itô Frameworks
Thomas Lew
Stochastic differential equations (SDEs) can be studied via Itô calculus and rough path theory. For
stochastic optimal control, these two frameworks give distinct Pontryagin Maximum Principle (PMP) optimality conditions with forward-backward SDEs (FBSDEs) or rough differential equations. We show that the adjoint equations of the Itô and rough PMPs are connected via the conditional expectation $p_t^{\text{It\^{o}}}=\mathbb{E}[p_t^{\text{rough}} \mid \mathcal{F}_t]$, where $\mathcal{F}_t$ represents information available at time $t$. First, we derive a rough
stochastic PMP for problems with adapted controls that does not use FBSDEs. Its proof extends the rough
stochastic PMP over deterministic controls by considering
stochastic needle variations. Second, we derive a unified PMP connecting the Itô and rough PMPs, using Itô-Stratonovich conversion formulas and duality identities between the forward tangent and backward adjoint SDEs. As a first application, we rederive the adjoint matching method for fine-tuning generative models. As a second application, we propose an indirect shooting method for a class of feedback problems. Overall, these results give a new conditional bridge connecting two popular frameworks for
stochastic optimal control.
Read the full abstract ▾
Machine Learning
Which Tasks Survive Self-Supervised Learning?
Achleshwar Luthra, Lucas Bryant, Tracy Zhu et al. (+1 more)
Same-instance self-supervised learning (SSL) learns representations by enforcing consistency across two views of the same underlying instance. This principle alone, however, does not determine which downstream tasks remain recoverable from the learned representation. We study this question through semantic recoverability, defined as the amount of a task's posterior score captured by the represented function space. We show that, for centered and whitened representations, recoverability exactly determines directional class-distance-normalized variance (CDNV), controls few-shot nearest-centroid classification, and governs the strength of task-relevant semantic directions. The population linear probe and centroid axis coincide, and multiple well-recovered tasks approach a factorial centroid geometry. We then analyze a canonical two-view SSL objective and show that its population optimum spans the leading cross-view-stable modes of the associated two-view operator. This yields a closed-form spectral characterization of semantic recoverability: a downstream task is preserved to the extent that its posterior lies in the selected spectral subspace. We validate these predictions on synthetic and real
datasets across several SSL methods, testing the predicted relationships among recoverability, directional geometry, spectral structure, and few-shot transfer. Together, these results give a task-level account of what information survives same-instance SSL and how the retained information appears in downstream geometry and transfer.
Read the full abstract ▾
All authors Achleshwar Luthra, Lucas Bryant, Tracy Zhu, Tomer Galanti
Machine Learning
LeanPolish: Verified Supervision for Lean Proof Compression
Pauline Bourigault
Verified proof edits offer a natural source of supervision for improving
language-model-generated Lean proofs. Yet verification establishes that an edit is correct, not that its training signal is free of search artifacts. We introduce LeanPolish, a symbolic Lean 4 pipeline that releases 33,402 accepted local edits and 65,596 same-state failed attempts, and use it to study what models learn from this supervision. First-success search admits a goal-independent rule with perfect ranking accuracy; teacher-selected evaluation sites also reward trivial deletions. Continuing menu evaluation beyond the first success removes the ordering shortcut: a trained ranker selects the best candidate on 70.1% of evaluated held-out states, versus 36.9% for the strongest frozen baseline. For compression, iterating the symbolic pass raises miniF2F savings from 19.7% to 27.5%, exceeding the neural hybrids we test there. Verified neural editing helps on other proof sources, but matched frozen-model controls show that its gains need not come from training. The supervision does improve whole-proof rewriting: fine-tuning raises verified
token reduction from 2.8% to 5.5% on 19 PutnamBench proofs. Together, the released edits, complete candidate pools, and controlled evaluations separate learning to imitate a search policy from improving on that search. They provide a reproducible basis for studying proof improvement while keeping correctness, compression, and edit policy distinct.
Read the full abstract ▾
Machine Learning
Learning to Plan from Random Exploration
Deqian Kong, Guangyan Sun, Sheng Cheng et al. (+6 more)
Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without policy-improvement training? Our random-walk analysis explains what temporal relations contain: short horizons reveal geodesic geometry in the
diffusion limit, while longer horizons reveal connectivity between regions before mixing removes these distinctions. We learn these relations with a conditional energy-based model that estimates temporal log-density ratios through horizon-conditioned
embeddings. The model is trained on observation pairs by noise-contrastive estimation, without action or reward labels. The planner queries these learned relations at different horizons as it moves toward the goal. At test time, a separate local dynamics model predicts candidate action outcomes, and the temporal model evaluates their progress toward the goal by selecting or aggregating estimated improvements across horizons. The
agent executes one action and replans with both models fixed. Experiments demonstrate long-range maze planning from random exploration using states and images. Learned score fields,
embedding probes, and planned routes exhibit properties of a multiscale cognitive map. We further demonstrate egocentric navigation from random exploration and manipulation planning from suboptimal data.
Read the full abstract ▾
All authors Deqian Kong, Guangyan Sun, Sheng Cheng, Sirui Xie, Bo Pang, Jianwen Xie, Tony Geng, Caiwen Ding, Ying Nian Wu
Machine Learning · Cross-listed from cs.AI
Aligned Data Can Induce Misalignment via Context Confusion
Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin et al. (+4 more)
Large
language models (LLMs) are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for preventing post-update misalignment. However,
alignment is inherently context-dependent: a recommendation that is aligned in one context may be inappropriate in another. For example, in response to the question "What should a researcher do with the research data?", recommending that the researcher preserve the data for reproducibility is aligned. In contrast, recommending data saving in response to "What should a mobile-app developer do with users' sensitive data?" may be inappropriate from a
privacy perspective. Starting from this observation, we identify a post-training phenomenon where aligned training induces misaligned behavior in other contexts. We call this phenomenon **context confusion**. We demonstrate context confusion across three domains: (1) Gender Equality, (2)
Privacy, and (3) Physical Safety. We further show that context confusion causes narrow misalignment, in contrast to emergent misalignment, and is not effectively reduced by injecting general
alignment data, but can be substantially reduced by including targeted
alignment data for the misaligned domain or providing in-context learning examples during inference. Lastly, we provide a mechanistic explanation of *context confusion*. We observe that queries from different domains can undergo similar representational shifts during the fine-tuning. Consequently, a query from a different domain may activate the same behavioral feature learned during fine-tuning, which causes the behavior to transfer to a context where it is misaligned. Based on our findings, we argue that it is difficult to predict the
alignment state of a model after training by inspecting the training data alone, which highlights the importance of comprehensive post-training
alignment evaluations.
Read the full abstract ▾
All authors Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin, Swastik Roy, Morteza Ziyadi, Salman Avestimehr, Sai Praneeth Karimireddy
Machine Learning · Cross-listed from stat.ML
Lower Bounds for Linear-Oracle Online Learning
Mohit Sinha
Can a constant number of linear minimizations per round improve on the $T^{3/4}$ regret rate of online Frank-Wolfe on general convex sets? Weibel et al. conjectured that fixed-coefficient methods cannot. We prove their
conjecture and extend the lower bound to every deterministic learner in an oracle-only model. The learner receives an initial feasible point and a diameter bound, and must remain feasible on every domain consistent with its oracle replies. For $T$ rounds, at most $b$ calls between decisions, diameter bound $D$, and gradient norm bound $L$, we construct an instance in dimension $d=2b(T-1)+1$ with regret at least $2^{-1/4}LDb^{-1/4}T^{3/4}$. The adversary fixes the domain, initial point, deterministic tie rule and linear losses before play. The vertices form a path on which every point available before a decision has zero current loss, while the final vertex has negative loss on every round. For constant $b$, the result matches the known upper rate for dimension-independent guarantees. For one-call fixed schedules with a nonzero coefficient on the newest gradient, a second construction gives regret at least $3LDT^{3/4}/4$ with unique minimizers at every issued query. Exact-arithmetic certificates for the tuned schedule of Weibel et al. closely match their finite-horizon numerical worst cases, with unique oracle replies.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Doc2LoRA Provides Decodable Representations of Scientific Ideas
Chand Sahil Mansuri, Joel Zachariah and Sadamori Kojaku
Representing scientific papers as points in a space lets us search for similar papers and inquire about how fields relate to one another and drive innovation. Beyond search, the vector space of papers invites generation: mixing papers through simple vector operations creates new points, mirroring combinatorial novelty, the recombination of existing ideas into new ones. However, a mixed point often represents an idea no paper has yet realized, with no papers nearby to identify the idea. We propose representing each paper by a LoRA adapter generated by the Doc-to-LoRA hypernetwork. Every point in the space, including mixtures, thus represents a large
language model (LLM) open to questions and instructions in natural
language. On papers from the American Physical Society (APS), we instruct the LLM at the average of each subfield to name the field in a few words and obtain labels closer to the official names than the labels of five baselines, as judged by word overlap and a panel of five LLM judges. We also ask the LLMs at points between two APS papers to write an abstract and obtain descriptions shifting from one paper to the other in step with the mixing weight. While Doc-to-LoRA is trained for generation, a small invertible transform makes the
embeddings competitive for search, on par with SPECTER2 and EmbeddingGemma and close to SBERT. Because the transform is invertible, every point in the transformed space still maps back to an LLM. The
embeddings thus serve both search and generation, enabling researchers to question the idea at any point in the space as a starting point for generating new ideas.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
Qiankai Xu
A harness is the code around a
language-model
agent that organizes
prompts, calls tools, manages context, and controls execution. As models grow stronger, recent work has begun to let
agents improve their own harnesses, a line of work known as self-evolving harnesses. In most existing methods, a separate proposer running on a human-designed harness modifies the solver's harness, and a separate harness is evolved for each
benchmark. Real-world tasks come from many domains, so both the
evolution and the evaluation of a harness should cover a diverse range of tasks. We propose a framework close to recursive self-improvement: the same frozen model, on the same version of the harness, first solves tasks as the solver and then, as the proposer, reads the complete run records and directly edits the harness that runs it. Each
evolution batch draws tasks from five
benchmarks in different domains. To measure generalization, training and held-out tasks are strictly separated, and we additionally evaluate on five out-of-distribution
benchmarks never used during
evolution. We frame the
evolution process as deep-learning training with two stages, multi-task pretraining and continual training. Starting from a 49-line seed harness, the harness obtained at the end of the first stage improves the average score by 4.48 points on the in-distribution
benchmarks and by 12.64 points on the out-of-distribution
benchmarks, surpassing Codex on the former and matching it on the latter. In the second stage, continued
evolution on Claw-Eval, one of the out-of-distribution
benchmarks, further raises the score on that
benchmark from 66.17 to 68.06, exceeding Codex. We also provide an in-depth analysis of the mechanisms that emerged during
evolution, including output truncation, history compaction, and independent review.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Acceleration of Diffusion Language Model through Discrete Average Generator
Yidong Ouyang, Zhengyan Wan, Themis Haris et al. (+8 more)
Discrete
diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few-step generation remains a fundamental challenge. In this work, we introduce the Discrete Average Generator, a principled extension of MeanFlow to Continuous-Time Markov Chains (CTMCs). Analogously to how MeanFlow defines an average velocity field over a time interval in continuous spaces, we define an average generator as the normalized increment of the transition kernel over a time interval. We show that this average generator satisfies a self-consistency identity, which provides the foundation for our training objective. We further develop training strategies that align with the standard training paradigm of
diffusion language models while keeping the resulting objective tractable. When projected onto per-coordinate marginals, the self-consistency identity admits a closed-form expression, enabling efficient training and inference. In Potts model simulations, our objective reduces the total variation distance of the $K$-step sampler by up to 67%. On OpenWebText, our method achieves the lowest generative perplexity among the evaluated methods for 8 to 64 sampling steps while enabling a $16\times$ acceleration, and achieves comparable performance to existing methods on ImageNet.
Read the full abstract ▾
All authors Yidong Ouyang, Zhengyan Wan, Themis Haris, Tian Tan, Liqian Peng, Henry Li, Ziqian Lin, Jianhang Chen, Maryam Karimzadehgan, Alec Go, George Michailidis
Machine Learning
Simulator-Refined Diffusion for Radio-Frequency Inverse Design
Jinhao Liang, Jacob K. Christopher, Michael Frei et al. (+2 more)
Diffusion models have shown potential in inverse design of printed
circuit boards (PCBs), enabling the generation of layouts conditioned on target S-parameters. Despite this promise, applying
diffusion models to PCB layout generation remains challenging due to their difficulty in meeting the quantitative electromagnetic specifications. A common approach is gradient-based guidance, which biases the
diffusion sampling process with the gradient of an objective used for evaluation. However, full-wave electromagnetic simulators are accurate but expensive and typically non-differentiable, whereas differentiable surrogates are informative but not always reliable. To address these limitations, this paper proposes Simulator-Refined
Diffusion (SRD), a novel combination of a low-fidelity differentiable surrogate and a high-fidelity non-differentiable simulator within the
diffusion sampling process. Unlike standard zeroth-order optimization, which requires a great number of random perturbations, our approach uses the surrogate's gradient to propose the perturbation direction while the simulator then searches based on this direction to identify an effective design update. Experimental results across different settings show that this method consistently outperforms current state-of-the-art methods, producing layouts whose simulated S-parameters match the target specifications up to 21.2% closer for in-distribution targets and up to 19.8% for out-of-distribution targets.
Read the full abstract ▾
All authors Jinhao Liang, Jacob K. Christopher, Michael Frei, Tommaso Dreossi, Nando Fioretto
Machine Learning
On the Off-Policy Teacher in On-Policy Distillation
Langlin Huang, Hao Liu, Mononito Goswami et al. (+5 more)
On-policy
distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its own policy under dense teacher supervision. However, OPD introduces a fundamental asymmetry: although the sampled trajectories are on-policy for the student, they are off-policy for the teacher. The teacher is typically optimized to continue from prefixes generated by its own policy, but during OPD it must instead supervise prefixes generated by the student. Empirically, we find that its continuation performance degrades as these prefixes grow longer. To address this issue, we propose Student-COnditioned Updates of the Teacher (SCOUT), a co-training framework that adapts the teacher to student-generated prefixes. Alongside standard OPD updates, SCOUT periodically optimizes the teacher's conditional ability using reinforcement learning with verifiable rewards, where the teacher generates continuations from student prefixes and learns from outcome rewards. Controlled experiments show that SCOUT improves the teacher's ability to continue from student-generated prefixes, supporting the intended mechanism of student-conditioned teacher adaptation. Across multiple teacher–student configurations, model scales, and
reasoning domains, SCOUT also consistently improves the effectiveness of on-policy
distillation.
Read the full abstract ▾
All authors Langlin Huang, Hao Liu, Mononito Goswami, Xinyu Li, Prithwish Jana, Nikos Kanakaris, Patrick Blöbaum, Purak Jain
Machine Learning · Cross-listed from cs.AI
Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks
Sumit Asthana, Michael Ion and Kevyn Collins Thompson
High quality synthetic data is central to post training LLMs for adaptive AI applications that represent the diverse expert strategies and decisions in conversations. Prompting LLMs directly or conditioning them on end use scenarios yields low diversity data that collapses onto dominant modes. We propose a method to generate diverse high quality synthetic data using Generative Flow Networks (GFlowNets). We show that training GFlowNets to generate latent conversation structure using a Gaussian mixture density over key interaction features (e.g., confusion episode dynamics, scaffolding directive balance) enables sampling expert strategies in proportion to their prevalence in the training data. Across two structurally distinct domains, tutoring and emotional support dialogues, our GFlow based synthetic data generation approach offers a better balance of fidelity, mode coverage and authenticity than reinforcement-learning and end to end LLM baselines, without copying training data. Evaluated on three downstream outcome prediction tasks, classifiers trained on synthetic GFlowNet generated conversations provide a stronger training signal than competitive synthesis baselines.
Read the full abstract ▾
Machine Learning
Continual Learning of Dynamical Systems in Recurrent Neural Networks through Recyclable Unit Gating
Sima Hashemi, Daniel Durstewitz and Georgia Koppe
Dynamical Systems Reconstruction (DSR) aims to infer models from observed time series that reproduce a system's qualitative long-term behavior. Continual DSR (cDSR) requires learning new systems while preserving previously learned dynamics, yet even small parameter updates in recurrent models can qualitatively alter their behavior over long autonomous rollouts. We
benchmark established continual learning (CL) methods spanning parameter regularization, replay, and parameter isolation on the fully trainable and interpretable Almost-Linear RNN (AL-RNN). Parameter isolation preserves earlier dynamics most effectively, but excessive task-specific allocations can rapidly exhaust a fixed-size network. We therefore introduce Continually-Recyclable Unit-Gating (CRUG), which conserves capacity through compact allocation and forward transfer. Differentiable gates trained with an $L_0$-based penalty select task-specific units, while unused units are recycled for subsequent tasks. Directed connections allow later tasks to reuse earlier representations without affecting the dynamics of previously committed units. CRUG achieves the strongest reconstruction–capacity trade-off among the tested methods with zero forgetting and reliably learns a heterogeneous sequence of nonlinear and chaotic systems. Furthermore, we show that forward transfer is more pronounced and useful when tasks share similar underlying dynamics. Lastly, we demonstrate that CRUG's advantages extend beyond autonomous cDSR to sequential cognitive tasks.
Read the full abstract ▾
Machine Learning
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
Prithwish Jana, Mononito Goswami, Hao Liu et al. (+9 more)
Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long-horizon performance, yet its combinatorial search space demands substantial human effort that must be repeated as models change. Existing automated methods explore this space narrowly, optimizing only components such as
prompts or skills or becoming trapped by fixed, exploitative search strategies. We introduce MILO (Meta-evolutionary Island Orchestration), a framework that co-evolves
agent harnesses and the strategy used to discover them. MILO combines: (i) hierarchical lineage
memory over island-based trees, using rejected mutations as negative evidence; (ii) per-island mutator
agents that rewrite complete harnesses using global search history and parent-specific feedback; and (iii) an orchestrator that adapts search through lineage grafting and speciation, mutator reassignment and curriculum revision. Across Terminal-Bench 2.1, PaperBench, and DeepSWE, MILO-discovered harnesses outperform eight state-of-the-art harnesses and six search methods using frontier (Opus 4.8) and open-weight (gpt-oss-120b) models. With Opus 4.8, MILO improves resolution over its initial harness by $+12.0\%$, $+28.3\%$, and $+10.3\%$, respectively, compared with best prior-search gains of $+4.5\%$, $+18.3\%$, and $0\%$. On Terminal-Bench 2.1, it achieves $86.1 \pm 2.0\%$, exceeding the official leaderboard's top entry ($83.8 \pm 2.3\%$) while using 26% fewer
tokens than its initial harness. On EinsteinArena open problems, MILO improves best-known upper bounds for Erdős minimum-overlap ($0.3808586 \to 0.3808568$) and the first and third autocorrelation inequalities ($1.50274365 \to 1.50274360$; $1.45081 \to 1.44889$).
Read the full abstract ▾
All authors Prithwish Jana, Mononito Goswami, Hao Liu, Xinyu Li, Langlin Huang, Zhehui Huang, Zhishen Huang, Patrick Blöbaum, Anoop Deoras, Purak Jain, Nikos Kanakaris, Sahika Genc
Machine Learning
Function-Space Transformer with Adaptive Anchors
Guorui Sang and Pedram Rooshenas
Many forms of data, including physical fields,
geometric shapes, and visual signals, are naturally described by functions over continuous domains but are observed through discrete samples. Representing these functions on fixed uniform grids imposes a trade-off between resolving localized variation and increasing computation across the domain. Neural operators address this mismatch by learning mappings between functions, while latent-
attention architectures provide flexible processing of sampled observations. We introduce the Function-Space
Transformer (FST), a framework for learning from functions through a spatially adaptive continuous latent representation. FST stores features at anchors whose locations are predicted from the input observations and recursively refines these anchor features through function-space interactions. This allows the representation to adapt its spatial organization to each input rather than inherit that of the observation grid, while supporting both spatially resolved and finite-dimensional outputs. On PDE solution prediction using PDEBench Burgers and Darcy flow, FST substantially outperforms the Perceiver IO baseline, whose latent representation lacks explicit spatial organization, and is highly competitive with the
Fourier Neural Operator. On ImageNet-1K, FST achieves higher classification accuracy than the
Vision Transformer baseline, with fewer parameters across these comparisons. Ablations further support the benefits of function-space updates and recursive refinement. Together, these results highlight the potential of adaptive continuous representations for both scientific prediction and visual recognition.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SE
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
Chun-Wah Hsu, Kai Gong, Yu Wu et al. (+12 more)
Multi-
agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations are followed faithfully, whereas reality differs. This behavioral gap, combined with differences in underlying system components, prevents clear attribution of observed gains. To this end, we introduce OpenCollab, a multi-
agent coding framework that provides a unified infrastructure for programmable collaboration and controllable runtime. Specifically, OpenCollab unifies organization design, enforces experimental control on a shared runtime, and tracks execution through fine-grained event streams. On this basis, we define Adherence to quantify whether the declared organization is actually realized. Our experiments reveal that
agents collaborate very differently across configurations: changing any single dimension shifts Adherence, from 47.2% to as high as 97.2%. Furthermore, extensive agentic coding
benchmarks show that OpenCollab (Duo) establishes new SOTA performance compared to the mainstream harnesses such as Mini-SWE-
agent, OpenHands, Codex CLI, and Claude Code, showing that a well-designed organization can outperform strong existing harnesses, while OpenCollab's single-
agent configuration uses the fewest
tokens across all evaluated suites. OpenCollab establishes a unified multi-
agent infrastructure for easy programmable collaboration and controlled causal evaluation.
Read the full abstract ▾
All authors Chun-Wah Hsu, Kai Gong, Yu Wu, Xianhe Chen, Mengyang Liu, Jie Li, Hanyu Li, Zhixuan Liu, Naisheng Tang, Jiaying Chi, Ziheng Fan, Xuning He, Xiaokang Yang, Xue Jiang, Yihong Dong
Machine Learning
Activation-Conditioned Self-Distillation
Zhexi Lu, Subhajit Chaudhury, Tejaswini Pedapati et al. (+2 more)
On-policy self-
distillation uses a model as its own teacher to provide dense supervision for
reasoning, often through reference-solution conditioning. Providing privileged information does not by itself ensure effective
token-level supervision throughout long responses. We introduce Activation-Conditioned Self-
Distillation (ACSD), which extracts a steering vector by contrasting activations of self-generated trajectories that reach verified correct answers within a generation budget with those of all remaining trajectories. A frozen copy of the base model applies this vector at each prediction position, and the student learns from its next-
token distributions on student-generated prefixes. Outcome verification is used for direction construction and calibration;
distillation requires neither problem-specific reference text nor teacher parameter updates. The distilled student is used alone at inference. On each of five models, ACSD achieves the highest mean accuracy over four mathematical
benchmarks among the evaluated methods. On DeepSeek-R1-0528-Qwen3-8B, mean mathematical accuracy reaches 71.9% and LiveCodeBench v6 pass@12 reaches 70.9%, compared with 69.0% and 66.3% for the reference-conditioned OPSD baseline. Contrasts among correct trajectories also support
distillation, and extracted directions can be reused across mathematical training
datasets. On fixed student trajectories, ACSD maintains more stable late-position logit-update magnitudes than OPSD.
Read the full abstract ▾
All authors Zhexi Lu, Subhajit Chaudhury, Tejaswini Pedapati, Keerthiram Murugesan, Lei Yu
Machine Learning
Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling
Xinyu Li, Mononito Goswami, Hao Liu et al. (+5 more)
Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires deciding how to allocate fresh contexts and what information to carry between them. We call a model's ability to make these decisions contextual
reasoning. Existing approaches largely prescribe these decisions through their harness; we instead shift them to the model. We introduce 1) Hermes, a family of simple, configurable harnesses that progressively varies model control over context allocation and reuse, and 2) Hermes-Learn, a two-stage framework for learning these capabilities. We find that capable models can exploit this flexibility to scale with additional inference-time compute, while smaller open-source models initially struggle to do so. Training with Hermes-Learn closes this gap, inducing adaptive contextual
reasoning strategies that vary with both the problem and the progress of
reasoning. These gains generalize across
benchmarks and models, extrapolate beyond the inference-time compute seen during training, and transfer to complementary test-time scaling methods beyond Hermes.
Read the full abstract ▾
All authors Xinyu Li, Mononito Goswami, Hao Liu, Nikos Kanakaris, Langlin Huang, Prithwish Jana, Patrick Blöbaum, Purak Jain
Machine Learning · Cross-listed from astro-ph.IM
Gestalt: a meta-foundation model for astronomy
Michael J. Smith and Shashwat Sourav
The Platonic Representation Hypothesis predicts that sufficiently scaled foundation models converge on a shared representation of the world. As each non-converged model gives a noisy view of a common structure when passed the same input, we ask whether we can combine models into a representation that outperforms its individual components. We test this on
galaxies: we embed images via a basket of 22 frozen foundation models from eight families, whiten each view, and take a randomised SVD of the
embedding concatenation. The resulting 1024-dimensional
embedding outperforms every basket member on 19/21 of our tested metrics for physical property and
galaxy morphology estimation for HSC, JWST, and DESI Legacy Survey imagery. We find that performance rises with basket size and basket architectural diversity, and that the meta-foundation model's performance transfers across astronomical surveys. We conclude that a useful astronomical foundation model can be assembled from existing generalist models with no training required beyond a single unsupervised projection. By leveraging the community's already-spent work, we save a lot of compute: a fresh pre-train of a comparable single-domain model would cost $\mathcal{O}(10^{4}$–$10^{5})$ A100 GPU hours (emitting several tonnes of CO$_2$eq.), whereas assembling Gestalt requires minutes on a single machine.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at $\epsilon \leq 4/255$
Binchi Zhang, Apurva Narayan and Atrisha Sarkar
Vision Language Models (VLMs) are widely deployed in safety-critical scenarios, and understanding to which extent they can be controlled by
adversarial perturbation is a prerequisite for evaluating their trustworthiness. Existing representation-
alignment attacks, which make a VLM perceive a target image, achieve limited success at $\varepsilon \leq 4/255$. Therefore, VLMs seems robust to perturbations in this range. We show that this robustness does not hold, as targeted semantic substitution succeeds within the same range. Specifically, we align each stream of the source image with its counterpart in the target image in the victim VLM's post-merger
token space, operating under a white-box threat model. We evaluate under a strict success criterion, requiring the model to simultaneously name the target, confirm its presence, and deny the source. In images, target semantics appear at $\varepsilon = 2/255$ and complete replacement reaches 38% at $\varepsilon = 4/255$. On
video, complete replacement reaches 35.9% at $\varepsilon = 1/255$. We also observe a phenomenon of semantic fusion, where Large
Language Model (LLM) rationalizes contradictory visual signals into a coherent narrative.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Privacy in Personalized AI Is a System Property, Not Just a Model Property
Guillaume Salha-Galvan and Jiaying Xu
In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broader systems that access, infer, and reuse user information across components and over time. While such use of user information is integral to personalization, it also raises important
privacy questions. In this paper, we argue that individual model- or component-level analyses may not capture all
privacy risks arising in such systems, motivating a system-level perspective on
privacy. We distinguish and analyze four interconnected
privacy-risk channels in personalized AI, and subsequently propose four requirements for system-level
privacy evaluation, covering interaction trajectories, internal information flows, indirect leakage, and the
privacy-utility trade-off. We argue for their systematic incorporation into
privacy audits of personalized AI.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.GT
Social Choice Foundations for Simulation-Augmented Generation
Sonja Kraiczy, Smitha Milli, Ratip Emin Berker et al. (+6 more)
Simulation-augmented generation (SAGE) is a recent technical proposal in which models simulate individuals' viewpoints at inference time in order to provide more representative answers to contentious user queries. A core challenge for SAGE is making inference-time simulation efficient without sacrificing representation quality. We introduce the first formalization of this problem, based upon an axiom from proportional clustering known as metric proportional justified representation+ (mPJR+) which is the strongest proportionality axiom known to always be satisfiable by centroid-based clustering. We prove that to proportionally represent the viewpoints of a population of $n_H$ humans on a given
prompt, we need only create simulations of $n \ll n_H$ individuals, and at inference time, need only dynamically route to $k \ll n$ of those simulations based upon the
prompt. This twofold reduction still yields approximate proportional representation guarantees for the entire population. Empirically, across two domains-political questions and personal advice-our proposed routing
algorithm achieves higher mPJR+ satisfaction rates than $k$-means-based or random selection baselines.
Read the full abstract ▾
All authors Sonja Kraiczy, Smitha Milli, Ratip Emin Berker, Avinandan Bose, Brandon Amos, Jamelle Watson-Daniels, Maximilian Nickel, Edith Elkind, Ariel D. Procaccia
Machine Learning
Kinematic signatures of impairment: Detecting alcohol intoxication in e-scooter riders using sensor data and machine learning
Rahul Rajendra Pai, Marco Dozza, Alexander Rasch et al. (+2 more)
Alcohol intoxication is a leading contributor to fatal and severe-injured e-scooterist crashes. Current countermeasures, such as temporal restrictions or pre-ride cognitive screening, cannot continuously assess an e-scooterist's physical motor control or impairment in real time. We conducted a controlled experiment in which 25 participants rode an instrumented e-scooter through a test track while sober and at two targeted blood alcohol concentration levels (0.05% and 0.08%). The e-scooter was instrumented with a six-axis inertial measurement unit (IMU), and throttle and brake lever position sensors, all sampled at 100 Hz. Two complementary signal features were computed: normalised permutation
entropy, which quantifies temporal complexity, and standard deviation, which quantifies signal amplitude. Repeated measures correlation identified seven kinematic features (all IMU and throttle signals) whose
entropy decreased (p < 0.001) while standard deviation increased (p < 0.01) with increasing intoxication, indicating that intoxicated riders shift from continuous, low-amplitude micro-corrections to fewer, high-amplitude reactive corrections. An
entropy based multi-class logistic regression classifier, evaluated through leave-one-participant-out cross-validation, achieved 85% overall accuracy and a weighted one-vs-rest area under the receiver operating characteristic curve (AuROC) of 0.94, with a sober-vs-high AuROC of 1.00. Steering rate and lateral acceleration were the most important predictive features, indicating that alcohol induces a distinct collapse in lateral
equilibrium during riding. Ultimately, these results demonstrate that onboard kinematic sensing combined with
entropy-based signal analysis can reliably distinguish sober from intoxicated e-scooter riding, providing a foundation for automatic intoxication detection systems that preserve mobility for sober riders.
Read the full abstract ▾
All authors Rahul Rajendra Pai, Marco Dozza, Alexander Rasch, Ali Mohammadi, Marco Capuccini
Machine Learning · Cross-listed from cs.CL
Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
Liangyu Teng, Hengsong Liu, Juncen Guo et al. (+4 more)
The performance ceiling of an LLM team is constrained not only by individual model capabilities, but also by inter-member error resonance and predictive differences. Although heterogeneous teaming is often observed to be effective in practice, existing approaches lack complementarity metrics that are computable, interpretable, and optimizable, leaving team composition to rely on heuristics. We propose a heterogeneity-driven team selection framework that performs offline profiling to characterize individual capability along with two complementary signals: one captures decorrelation in error patterns to reduce co-failures, while the other measures divergence in predictive behavior to capture strategy diversity. We formulate team selection as a standardized quality–complementarity combinatorial objective and apply an efficient greedy search to select a small team from a candidate pool. Experiments across multiple
benchmarks demonstrate that our framework consistently outperforms quality-only baselines under controlled candidate pools and team sizes, establishing reusable selection principles for multi-LLM systems.
Read the full abstract ▾
All authors Liangyu Teng, Hengsong Liu, Juncen Guo, Jingyu Zhang, Yang Liu, Jing Liu, Liang Song
Machine Learning · Cross-listed from cs.CR
VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents
Yurong Hao, Wen Zhou, Guowei Guan et al. (+3 more)
Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous
agents, whose semantic states are dynamically refined through a recurrent process known as collaborative reflection. While this mechanism improves recommendation quality, it simultaneously introduces a systemic vulnerability:
adversarial evidence injected into a single
agent can be rationalised into a legitimate preference narrative, written back into
memory, and propagated to other
agents through interaction contexts. We term the local rationalisation process reflection laundering, and its system-wide escalation through collaborative reflection collaborative-reflection hijacking. Existing attacks on recommender systems, whether based on interaction-level data poisoning or text-level
adversarial perturbations, assume static pipelines and thus cannot exploit this recurrent, multi-
agent amplification pathway. To bridge this gap, we first conduct a controlled vulnerability analysis that establishes two exploitable properties underlying collaborative-reflection hijacking: reflective persistence and cross-
agent propagation. Then building on these findings, we propose VirusCascade, the first black-box targeted promotion attack that jointly shapes semantic and structural attack surfaces: the former ensures the target item is naturally rationalised as satisfying broad user preferences, the latter positions it for system-wide propagation. Extensive experiments on four real-world
datasets across diverse LLM-ARS architectures demonstrate that VirusCascade consistently achieves state-of-the-art targeted exposure under evaluated stealth constraints, reaching a mean E@20 of 0.384 and surpassing the strongest baseline by an absolute margin of +0.185.
Read the full abstract ▾
All authors Yurong Hao, Wen Zhou, Guowei Guan, Tiantong Wu, Fuyao Zhang, Wei Yang Bryan Lim
Machine Learning · Cross-listed from stat.ML
Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions
Daniela De Canditiis, Italia De Feis and Paola Stolfi
Feature selection in neural networks remains a challenging problem, particularly in the presence of noisy or contaminated data. LassoNet is a recent approach that addresses this issue by combining neural networks with hierarchical sparsity constraints, enabling simultaneous prediction and variable selection. However, its standard formulation relies on the mean squared error (MSE) loss, which is known to be highly sensitive to outliers. In this paper, we present Robust LassoNet, an extension of LassoNet that incorporates robust loss functions, such as Huber, Cauchy, Tukey's bisquare, and Nonnegative Garrote, to mitigate the effect of extreme observations. The proposed approach preserves the original optimization framework while improving stability under data contamination. Through experiments on synthetic and real
datasets, we show that robust LassoNet significantly improves both predictive performance and feature selection accuracy in the presence of outliers or heavy tailed noise, while maintaining comparable performance in clean settings. These results highlight the importance of robustness in neural network based feature selection and suggest practical guidelines for choosing appropriate loss functions.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Inference-Layer Security: Defending Against Adversarial Inference and Infrastructure Abuse
Keifer Lee
A Technical Report: Operating a large
language model (LLM) as a service requires more than inference infrastructure: the provider must also defend against
adversarial interactions that seek to exploit the service, including jailbreaking for harmful use, sophisticated denial of service, and
distillation attacks. We study this problem at the inference layer, using a hypothetical frontier lab, Five Elements Inc., as a running example. Because no public labelled
dataset of
adversarial LLM usage exists, we introduce a structural causal model (SCM) that generates a realistically grounded, labelled
dataset of user-sessions, with coordinated multi-account campaigns, platform feedback, and three tiers of label observability. On this
dataset we train a practical gradient-boosted detector that classifies each user-session as benign or malicious and, if malicious, by attack type. Against oracle labels the detector very nearly solves the binary task (AUPRC $0.993$), yet against the operational labels a real Trust & Safety team would hold, the same model scores an AUPRC of only $0.313$: the detector is more accurate than the labels used to evaluate it. For attack-type attribution, a naive argmax is dominated by the $98\%$ benign prior (macro-F1 $0.295$), whereas a simple thresholded decision engine raises macro-F1 to $0.489$ without sacrificing accuracy. The
dataset is publicly released.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Skill-Space Shooting for Autonomous Robot Policy Improvement
Zihang Rui, Renhao Wang, Haoxu Huang et al. (+1 more)
Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this improvement to scale across tasks, it must make effective use of experience without requiring human demonstration of each correction. Recent agentic systems offer a way to reduce this reliance on human effort by using foundation models to autonomously compose learned behaviors to complete tasks. Yet completing tasks this way does not itself teach a task policy to overcome its own failures; that requires turning these behaviors into learnable corrections for the policy. Our insight is that many such corrections are familiar short behaviors, or skills: they recur across tasks and describe actions that foundation models can reason about from a scene. We introduce skill-space shooting, which uses foundation model guidance to explore corrections through these reusable skills and turn successful trials into policy improvement. Real-world experiments show repeated improvement in policies acting autonomously, while skills can also be shared to reduce the teaching needed to improve on new tasks. By making reusable skills a source of corrective supervision, skill-space shooting enables scalable and generalizable policy improvement within and across tasks. Additional results and
videos at https://skill-space-shooting.github.io.
Read the full abstract ▾
All authors Zihang Rui, Renhao Wang, Haoxu Huang, Yang Gao