Research

• Dynamic model and policy routing for general-purpose AI1 paper raises it · 1 addresses it

  Balancing performance and computational cost across diverse tasks and modalities is critical for scalable AI systems.

  • Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systemsraises · addresses
• Cross-repository consistency in coding agents1 paper raises it · 0 address it

  Real-world software development often requires coordinated changes across interdependent repositories, which current agents struggle to maintain.

  • CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agentsraises
• Efficient long-video generation with consistent quality1 paper raises it · 1 addresses it

  Real-time streaming video generation demands continuous output without quality degradation or camera drift.

  • Wave Forcing: Towards Speed-of-Light Streaming Video Generationraises · addresses
• Local decision-making for reasoning compression1 paper raises it · 1 addresses it

  Reducing inference costs without sacrificing accuracy requires models to know when to stop reasoning.

  • Think Less, Locally: Local Preference Learning for Reasoning Compressionraises · addresses
• Unified taxonomy and coordination for agentic systems1 paper raises it · 1 addresses it

  Fragmented terminology and rapid growth in agentic systems hinder systematic understanding and collaboration.

  • Advances in Agentic Computer Graphicsraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.AISep 30

  Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability

  Jeffrey Willette, Krishna C. Puvvada, Boris Ginsburg

  Long-horizon agentic workflows require models to sustain repeated state-dependent actions all while the context grows, sub-task complexity changes, and new data arrives. Each situation represents an independent axis along which an agent may fail. An agent reconciling a long ledger, for example, must repeatedly read its state, update the correct record, and preserve alignment across thousands of outputs. A model may accept the entire ledger yet lose its place or stop applying the operation consistently as generation proceeds. We introduce Long-Transduction, a controlled diagnostic that tests a model's ability to stay on task during long generation while continuously reading, mutating, and outputting input-context dependent operations such as arithmetic, sorting, variable lookups, and table transformations. Long-Transduction evaluation independently varies local task complexity, input data formatting, and context length isolate failures along each axis. We evaluate seven open-weight models, finding a 62.8\% decrease when scaling context length from 4-128K, a 36.5\% decrease when varying input format, and a 39.9\% decrease by increasing local task complexity. Together, these…

  PDF

  Summarize this
• arXiv cs.CVSep 30

  SCALE: Synthetic Calibration via Agreement Labeling in Embedding Space

  Wenjun Liu, Saeed Hassanpour

  Foundation models for computational pathology are usually evaluated using AUC and accuracy, while calibration is often left untested. This matters because a model can be accurate on average but still assign overly confident probabilities to cases that are difficult even for pathologists. We study calibration across eight pathology foundation models. Using pathologist agreement as a measure of diagnostic difficulty, we find that calibration error is consistently higher on low-agreement cases than on high-agreement cases. This pattern is not apparent from aggregate expected calibration error (ECE) alone. We then propose synthetic agreement calibration, a method for improving calibration without collecting multi-annotator labels. Given a trained linear probe, we select high-confidence embeddings as class anchors and interpolate between anchors from opposite classes. The interpolation weights encode a continuous notion of diagnostic ambiguity, which we use as a synthetic agreement signal to retrain the probe with agreement-aware label smoothing. On MHIST, which includes annotations from seven pathologists, synthetic agreement calibration recovers most of the calibration improvement…

  PDF

  Summarize this
• arXiv cs.AISep 30

  Budget Boundary Effects in Test-Time Mathematical Reasoning

  Guilin Zhang, Ziqi Tan, Wulan Guo, Kai Zhao, Hongyun Yang +3

  A cumulative token cap can fall inside a mathematical derivation, forcing a test-time controller to choose between stopping at the cap (strict) and allowing the current attempt to finish (advisory). We measure this boundary choice with paired offline replays of 19,200 public traces: 120 AIME, BrUMO and HMMT problems and two archive configurations of one model. Candidate order and a 16-attempt cap are fixed, and answer selection is blind to reference answers and correctness labels. Three findings emerge. First, at the 4k cap, most advisory accuracy gains replace abstention with a correct answer; strict stopping pays for an unfinished prefix that the completed-only selector cannot use. Second, comparisons along realized cost differ from same-cap comparisons: advisory 4k in low has higher accuracy than strict 8k at comparable mean completion cost, while in high its observed accuracy is 0.42 points below strict 32k using 59% of its mean tokens. These aggregate comparisons do not establish equal-compute superiority or accuracy equivalence. Third, increased candidate coverage does not guarantee higher answer accuracy: a log-probability selector loses accuracy while coverage rises,…

  PDF

  Summarize this
• arXiv cs.DCSep 30

  Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI Infrastructure

  Matias Parij, Pawan Paudel, Tate Berenbaum, Muthaiah Venkatachalam

  We present Cascadia, a system for serving large language models on fleets of commodity Intel AIPCs using their CPU, integrated-GPU, and NPU resources. Every node embeds ingress, scheduling, and execution; inference requests require no dedicated routing control plane. Nodes join a libp2p QUIC mesh using CA-issued ed25519 admission certificates, gossip signed capabilities, exchange live load over direct peer streams, and route OpenAI-compatible requests to eligible peers. An operator-run certificate authority handles admission and fleet management outside the inference path. Three serving modes share one interface: whole-model execution on one node, load-balanced replicas, and pipeline-sharded chains using the compilation and speculative decoding mechanism of our companion paper. Optional KV-cache mobility reuses compatible conversation prefixes after a routing move, with cold recomputation on a miss. Signed response receipts and hash-chained logs support provenance and audit. A three-node Phi-3.5-mini NPU testbed delivered 3.10x the response throughput of its one-node configuration under ten concurrent requests; a separate four-node deployment recorded 4.06x the throughput of…

  PDF

  Summarize this
• arXiv cs.CRSep 30

  Proof-Gated Signing: Solver-Checked Transaction Guards that Hold Under State Drift for Onchain AI Agents

  Bravish Ghosh

  AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of defense is a pre-signing check: a static allowlist, an LLM reviewer, or a transaction simulation. All three share a gap: the check describes the chain state at check time, but the transaction executes in a later state that an adversary can shape through front-running, contract upgrades or token-parameter changes. We call this state drift. We present Proof-Gated Signing (PGS), which simulates a proposed transaction, extracts its effects, and uses an SMT solver to check a declarative value-and-permission policy for every price in an oracle-uncertainty band. It then compiles on-chain post-conditions (wallet balance bounds, payee receipts, allowance caps and ownership) and proves that every execution satisfying them also satisfies the policy. The agent's smart-contract wallet enforces them atomically, so the guarantee applies to the executed transaction under arbitrary drift. On an open testbed of 260 scenarios (14 attack families including five drift and two adaptive families, and 12 benign families), with harm measured from attacker…

  PDF

  Summarize this
• arXiv stat.MESep 30

  Always-On Experimentation

  Ricardo J. Sandoval, David Arbour, Avi Feller, Michael I. Jordan

  Generative AI has dramatically accelerated the rate at which new treatments---from novel pharmaceuticals to online marketing campaigns---can be conceived and deployed. As a result, modern experimentation platforms often run continuously, with treatments added as they are ready and removed when they underperform. We formalize this "Always-On" experimental setting, in which treatments can be dynamically generated, added to, and removed from a running experiment, and study the statistical problem of deciding whether to accept or reject each treatment while controlling for the false discovery rate. We develop sequential tests that achieve time-uniform Type-I error control under arbitrary stopping times and "predictable" treatment schedules. Our approach builds on the testing-by-betting framework: we construct test supermartingales for testing the average treatment effect of each treatment, and show that the construction of these test supermartingales is growth-rate optimal in an almost-sure sense.

  PDF

  Summarize this
• arXiv cs.CVSep 30

  No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation

  Zejing Rao, Ketong Ren, Xiaoqiang Liu, Yiping Meng, Guoxin Zhang +1

  Streaming video generators allow users to dynamically modulate video synthesis via mid-stream prompt switching. Existing streaming methods can respond to the updated instruction while still cutting corners, prematurely realizing goals or taking heuristic shortcuts that bypass necessary intermediate state changes needed for a plausible transition. In this study, we present SEGUE, a novel framework that makes this process explicit and trains the generator to execute these transitions faithfully. At each switch, a training-free planner parses the latest frame and prompts, writes a few segue prompts with roles and durations, and then hands control back to the user's prompt. Furthermore, to address the inherent difficulty of training causal models on short-lived temporal schedules without corrupting preparatory supervision, we introduce SPANDMD, which evaluates each active prompt using the full rollout as temporal context while retaining its DMD residual only within the prompt's assigned span. On OpenTrans-360, a benchmark of 1,800 switches that scores how the old state exits and the new one begins, SEGUE ranks first on all eight transition metrics and raises the overall score over…

  PDF

  Summarize this
• arXiv cs.AISep 30

  GATE-ST: Gene-Aware Text-image Encoder for Spatial Transcriptomics

  Lucas Ni, Jian Luo, Wentao Huang, Chao Chen

  Spatial transcriptomics enables spatially resolved gene expression analysis from slide-level images while preserving morphological features, providing valuable information for studying disease mechanisms and developing treatments. However, spatial gene expression profiling typically requires expensive and time-consuming tests. While existing image-based prediction optimizations mostly revolve around including positional embeddings and further image-based changes, text-based optimizations remain relatively unexplored. We present GATE-ST, which incorporates text-based inputs into image-based spatial gene expression predictions. With this approach, generated text descriptions of genes are utilized to better spatial transcriptomics prediction results. Gene summaries are put through a text encoder, generating embeddings that integrate with image embeddings through cross-attention layers to align with morphological features. We demonstrate the effectiveness of such text inputs by benchmarking performance against random gene embeddings and multiple other image-text fusion architectures, and show that GATE-ST outperforms these alternatives. Our results demonstrate the effectiveness of…

  PDF

  Summarize this
• arXiv cs.CVSep 30

  EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation

  Debabrata Mandal, Dongdong Fu, Jonathon Miller, William Villareal, Xi Peng +1

  Immersive displays can enable rich and diverse virtual experiences. Manually authoring every possible experience to realize this potential, however, is prohibitively expensive, difficult to scale, and impractical. Generative AI models could remove this bottleneck, but today's models are built for conventional displays and cannot generate the high-resolution, stereoscopic $360^\circ$ content required for immersive viewing. Further, temporal and stereo inconsistencies that may be tolerable on conventional displays can become highly disruptive when viewed through an immersive headset. Here, we address this gap with a zero-shot generative pipeline that extends existing video diffusion models into 4K stereoscopic $360^\circ$ videos. Inspired from binocular vision and depth perception, we develop an epipolar-aware $360^\circ$ image matching metric that captures the temporal and stereo geometric inconsistencies across views. We then use this metric as a preference signal for direct preference optimization with limited training data. Our work enables $360^\circ$ stereo video generation and provides a scalable path for bringing generative content to immersive displays, allowing diverse…

  PDF

  Summarize this
• arXiv cs.AISep 30

  JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion

  Zhengkai Tu, Mingda Zhang, Zijia Wang, Xiaoying Tang, Jimmy Huang

  A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounded discretion, benchmarks score a label or a rubric, and the experience that would supply the balance stays unverified. We formalize legal judgment as a reference-anchored task, whose object is a single decision that stays tied to the statute and to the circumstances at once. We introduce JusticeAxis, 256 real-world criminal cases from 18 countries with audio, image, and text evidence, and three lawyer-written judgments for every case: the recorded one and one for each failure. We further propose JusticeAgent, a harness whose element agents establish the facts and whose judge agent applies the law under skills carrying experience of the circumstances. Skills are distilled from execution trajectories and admitted only under Bayesian credible bounds. Experiments show that failure turns direction with scale: open-weight backbones drift to unsupported grounds, frontier models to the statutory default. We further verify that JusticeAgent, as a simple yet effective plugin, carries a frozen open-weight backbone…

  PDF

  Summarize this
• arXiv cs.AISep 30

  Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic Status

  Sachin Dev Duggal, Pradyumna Swarnalatha Ramanna, Alexandros Vassiliades

  Knowledge-intensive language-model systems typically represent external knowledge as text chunks or static graphs, with limited support for concept evolution, point-in-time reasoning, and distinctions between validated and inferred knowledge. We introduce the Concept Lifecycle Model (CLM), which represents concepts as persistent, graph-grounded, temporally versioned entities with explicit provenance and epistemic status, and Concept-Grounded Attention (CGA), which injects concept-graph structure into transformer computation through graph-biased self-attention (Form A) and gated cross-attention over concept nodes (Form B). We evaluate the framework in controlled settings using disabled-mechanism baselines. On 200 MuSiQue and HotpotQA questions with retrieval fixed, concept-graph retrieval recovers explicit multi-hop paths but does not improve evidence recall. Form A appears to steer attention, with 2.76 times more attention on gold than distractor concepts, but the same ratio occurs when Form A is disabled; the learned bias is negligible and no answers change. An identity-preserving Form B improves F1 from 0.188 to 0.221, but control concepts yield 0.213, indicating that most of…

  PDF

  Summarize this
• arXiv cs.CVSep 30

  Unveiling the Value of Motion for Cinematic Camera Trajectories

  Ziqi Zhou, Yujian Yuan, Laura Sevilla-Lara

  Cinematic camera motion is a fundamental storytelling tool, defined not only by where the camera is positioned in the scene, but also by how it moves in terms of direction and speed. Recent work on camera trajectory generation and alignment to text relies on pose-centric representations. While in principle a network could derive direction of movement and speed, we find that in practice this might not happen. In fact, in this paper we discover that decomposing the camera trajectory representation from the traditional per-frame poses to direction and speed has surprising benefits across multiple tasks, including trajectory-to-text alignment as well as text-to-trajectory generation. To accurately evaluate the former, we introduce a simple and reliable protocol that overcomes the limitations of prior evaluation baselines. For the latter, building on this representational insight, we propose a novel generative model for camera trajectories, CineGEN, that achieves superior performance across a variety of metrics. We also propose a novel dataset, CineScript, containing movie clips that are enriched with scene descriptions as well as higher-level metadata. This novel data allows us to…

  PDF

  Summarize this
• arXiv cs.CVSep 30▲ 1

  ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

  Shubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah, Narendra Ahuja

  Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images. Increasingly, these images come from a diffusion model rather than a camera. We show that fine-tuning on such synthetic images degrades subject fidelity, producing oversaturated color and excess high-frequency detail. To isolate the cause, we fine-tune two models from the same base model with the same DreamBooth recipe, one on real photos of a subject and one on synthetic images of that subject generated by the first. We trace the degradation to classifier-free guidance (CFG). For the model personalized on synthetic images, the angle between the conditional and unconditional noise predictions, and with it the norm of their difference, is much larger than for the model personalized on real photos. This inflation grows toward high frequencies and also appears at other prompts semantically close to the subject, such as its class noun, but not at unrelated ones. We propose ReGain, a training-free correction applied at sampling time that measures how much each frequency band of the guidance is inflated relative to the base model and scales that band down accordingly.…

  PDF

  Summarize this
• arXiv cs.LGSep 29

  In-Distribution Imagination for Model-Based Offline Reinforcement Learning

  Mintae Kim, Koushil Sreenath

  Model-based offline reinforcement learning (MBORL) improves sample efficiency through model-generated trajectories. However, accumulative model error can drive imagined trajectories outside the offline data distribution, leading to unrealistic synthetic data and unstable policy optimization. Many existing methods primarily control rollouts using transition-level uncertainty. We propose \emph{in-distribution imagination} (IDI), a rollout control framework that estimates trajectory support in a learned representation space and adaptively truncates rollouts that leave the offline trajectory manifold. Combined with trajectory-regularized RL, an extension of entropy-regularized RL, IDI consistently improves performance in limited-data settings. Experiments show that trajectory support predicts rollout failure substantially better than transition-level uncertainty, highlighting the importance of trajectory-level rollout control in MBORL.

  PDF

  Summarize this
• arXiv cs.LGSep 29

  Provable Test-Time Scaling for Beam Search in LLM Reasoning

  Qijia He, Yu Huang, Yuan Cheng, Yuxin Chen, Yingbin Liang

  Beam-search-based test-time methods provide an effective way to improve large language model (LLM) performance on long-horizon generation by pruning invalid reasoning paths early, leading to significantly improved reasoning efficiency and more favorable test-time cost scaling. Despite strong empirical success, the theoretical understanding of beam search remains limited. In this paper, we study the test-time compute guarantee of the commonly used beam search framework that uses the model's internal log-likelihood for intermediate scoring, while relying on an external reward model only after a complete response is generated. We first establish a lower bound for vanilla beam search, showing that at least $Ω(C^\star(x)^2)$ samples are required for the optimal response to survive, where $C^\star(x)$ is the token-level coverage coefficient for prompt $x$. This motivates our modified confidence-filtered beam search (CF-Beam), which reduces the sufficient coverage dependence from quadratic to nearly linear under prefix competitiveness, for fixed horizon, gap, and target accuracy. We then show that the regret of CF-Beam is upper-bounded by the probability of rare failure events and the…

  PDF

  Summarize this
• arXiv cs.AISep 29

  Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts

  Hongmin Li, Wanli Zhao

  Final-answer accuracy does not reveal whether a scientific-search agent failed to encounter a target paper, attempt to inspect it, or return an accepted answer after inspection. We introduce decision checkpoints that record observations and tool actions without benchmark labels during inference, then join target identities and evaluator labels to assign outcome categories from recorded events. Across five conditions on 540 answerable AutoResearchBench Deep questions in a fixed, target-enriched environment, keyword search achieves 24.6\% accuracy, compared with 17.8\% for raw search. The keyword condition has fewer incorrect answers with neither target exposure nor inspection, but more incorrect answers after the target is exposed and left uninspected. Compared with keyword search, read-first has 27.4\% more recorded evidence-search calls. Target inspection attempts occur on 199 questions under read-first and 191 under keyword search; both conditions achieve 24.6\% accuracy. The checkpoint protocol makes these question-level differences explicit, distinguishing target exposure and inspection from aggregate accuracy and total tool use.

  PDF

  Summarize this
• arXiv cs.LGSep 29

  Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives

  Qiwei Di, Xuheng Li, Kaixuan Ji, Chenggong Zhang, Heyang Zhao +1

  On-policy distillation (OPD) learns from teacher feedback on student-generated responses and has shown promise in reducing forgetting relative to supervised fine-tuning (SFT). However, its benefits and fragility remain incompletely understood. We study sequential distillation from multiple teachers, where the student minimizes its average divergence from the teachers. Forward Kullback--Leibler (KL) divergence yields a weighted arithmetic mixture, while reverse KL yields a normalized weighted geometric aggregate. We develop algorithms that learn these targets under off-policy and on-policy feedback, respectively, establishing logarithmic regret bounds in the tabular setting and extending the analysis to function approximation. By analyzing these aggregation targets, we identify mechanisms that help explain both the benefits and fragility of OPD. Relative to forward KL, reverse KL can better retain a confident expert's preferences under uninformative feedback, but is more sensitive to teachers that assign very low probabilities to correct responses. Its token-level conditionals also reveal a dependence on continuation distributions that can favor incorrect prefixes over long…

  PDF

  Summarize this
• arXiv cs.MAAgentsSep 29

  CollabFlow: Recursive Self-Improvement of Agent Collaboration

  Xiao Huang, Mingda Zhang, Junming Zhang, Qiang Huang, Hanwen Zhang +3

  Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outcomes improve how they collaborate across tasks. However, existing multi-agent collaboration leaves this loop open: collaboration is pre-defined at the operator level, topology-only learning keeps verbatim exchange that propagates errors, and reward maximization on a system's own outcomes concentrates on a few teams. To address these challenges, we propose CollabFlow, an RSI system of Learned Agent Collaboration: a trainable Collab-Director constructs teams of complete Agents, a frozen executor runs them, and each round's outcomes retrain the director. Within each round, the edges of a collaboration graph carry protocols of Evidence-Conditioned Communication: a receiver adopts a differing answer only when the sender's evidence is stronger by a margin, so the director learns who communicates and how. Across rounds, we further propose Collaborative Trajectory Balance (CTB), a flow-based objective that credits each team once across its construction orders and targets a reward-proportional distribution over teams, so several…

  AI80PDF

  Summarize this
• arXiv cs.AISep 29

  EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment

  Mingda Zhang, Hanwen Zhang, Qiang Huang, Zijia Wang, Pengfei Guo +3

  In recent years, LLM-based multi-agent systems have been widely applied to orchestrate tool-using agents into executable communication graphs. However, existing self-evolving orchestration still faces key challenges, including post-hoc evolution that revises the team only after the trajectory ends, credit diffusion that gives every action the same terminal advantage under confounded baselines, and skill admission that is uncalibrated and never retired. To address these challenges, we propose EvoSteer, a new paradigm of Online Self-Evolving Graph Orchestration -- the orchestrator builds a running team and repairs its plausible but failing steps from execution features and a learned value estimate. To support this paradigm, we introduce Anchored Trajectory Balance (AnchorTB), a regression-style flow-matching loss that assigns each orchestration action a coefficient by balancing subtrajectories against a frozen reference. Built on the learned flow, we further propose Validated Skill Admission, in which a candidate skill is tried before promotion and promoted only if paired evidence passes a sequential test under a shared nominal testing budget. Moreover, AnchorTB combines measured…

  PDF

  Summarize this
• arXiv cs.CLSep 29

  Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation

  Haibo Jin, Xinjie Li, Najmeh Sadoughi, Yang Liu, Yibo Wang +2

  Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style. Existing single-LLM methods are largely sentence-level, and multi-agent systems often use static workflows that do not adapt to scene complexity or production context. We propose SMART, a Self-evolving Multi-Agent system for long-foRm subtitle Translation. During test-time training, SMART builds persistent series-level memory and translates a subset of sentences through a dynamic router and Mixture-of-Agents layer with tools for terminology verification, subtitle constraint validation, and contextual retrieval. A judge-refiner loop scores candidates and uses textual critiques to update agent prompts and routing policies without retraining the underlying LLMs. During test-time inference, the evolved configuration translates the remaining series. We also introduce Subtitle Arena, covering 14 genres, 2--198 episodes per series, production years 1959--2023, and 15 target locales, together with SubMQM, a subtitle-adapted MQM framework with seven dimensions and 19 error categories. SMART achieves the best overall…

  PDF

  Summarize this

• Spiking neural networks8+33.3%
• Character recognition OCR42+23.5%
• Quantum machine learning27−3.6%
• Voice AI62−13.9%
• Speech emotion18−14.3%
• Diffusion priors20−20.0%
• Channel state information16−20.0%
• Robotics157−24.2%