Automatic multi-agent workflow generation now targets execution time: LAWA cuts total makespan through graph edits aimed at critical-path bottlenecks while keeping competitive task performance across seven benchmarks.
SymAnt merges a scene graph and a knowledge graph into one joint graph and uses the symbolic context found by graph search as the starting point for iterative decoding, so it can predict long action sequences from very short observation windows. In the short-observation settings of Breakfast and 50 Salads, its mean accuracy over classes exceeds the neuro-symbolic baseline NeSCA and several large-model baselines; on EPIC-KITCHENS, the 3M-parameter model performs comparably to fine-tuned models with billions of parameters. Because predictions are anchored in an editable graph, users can add or remove nodes at inference time to change predictions without retraining.
Epidemic interventions are textual policies, yet a plain LLM lacks the epidemic dynamics to project their consequences, the surveillance signals to judge severity, and the institutional constraints on admissible actions. EpiWorld grounds an LLM policy agent in an action-conditioned epidemiological world model, screens candidate interventions through counterfactual rollouts, and distils simulated outcomes into reusable lessons. On retrospective COVID-19 and influenza data, the full configuration cuts 8-week cumulative hospitalisations by 59.3% versus the reference historical policy on real US Omicron, and by about 16% on average across six LLM backbones.
The work argues that low-dimensional topology such as Morse theory offers a strong, complementary, and largely unexplored perspective for machine learning; it introduces concepts from cobordism theory and harnesses discrete Morse theory tools to improve graph diffusion models through a pipeline called MG-Diff, derives theoretical guarantees and sufficient conditions showing that under a positive decision-gap the Morse-theoretic tools and their use for induced diffusion guidance are stable under small perturbations, and illustrates the utility of discrete Morse theory for spatio-temporal graph forecasting and graph regeneration.
The work proposes a PAC-private diffusion model adaptation that first learns a compact data-dependent component via LoRA or Textual Inversion and then calibrates anisotropic Gaussian noise from the covariance of repeated mechanism outputs, perturbing the learned component only once after optimization to avoid privacy composition across gradient updates; on few-shot concept personalization and full-dataset image synthesis it better preserves subject identity, generation quality, and downstream classification accuracy than DP while achieving the same reconstruction privacy.
The work proposes Self-Reflection Fine-Tuning (SRFT): it injects attack instructions into clean expert trajectories, samples the agent's own potentially failing actions under the attacked context, and has an expert model generate structured self-reflection reasoning that contrasts unsafe and optimal actions, which then supervises fine-tuning; instantiated as SR-Agent on Llama-3.1-8B-Instruct and Qwen3-8B, it reduces AgentDojo attack success rate from 7.59% to 1.26% and from 16.97% to 1.05% respectively, and keeps a low attack success rate under the RL-Hammer adaptive attack.
Observing that video and audio are perceived together yet most generative models treat them in isolation, this survey casts joint generation, cross-modal generation (one modality from the other) and joint editing as three problems defined on a single distribution over audio-visual pairs, organizes the field around one question—how the output is kept coherent across modalities in time and semantics—proposes a taxonomy along five design axes (generation strategy, audio representation, video representation, alignment enforcement, pretraining reuse), and, to the authors' knowledge, provides the first systematic taxonomy of joint audio-visual editing, mapped as nine edit categories spanning 28 edit types, together with methods, datasets and metrics for each setting and a closing list of open pr
The work reframes LLM routing as coverage-oriented subset selection, uses a determinantal point process to capture both model competence and inter-model redundancy, and trains with a failure-set-marginalization objective that directly maximizes the probability that at least one selected model answers correctly, achieving higher average Success@10 (0.8632 and 0.9914) and more diverse subsets on the medium-pool (3811 candidate LLMs) and large-pool (5000 candidate LLMs) RouterEval settings, while an adaptive greedy stopping rule sets subset size per query.
The authors formulate Rhetorical Robustness as a joint requirement (stable judgments under content-preserving rewrites plus discrimination across papers), build RobustReview from 60 anonymized ICLR 2026 submissions under 10 rhetorical conditions for 1,260 full manuscripts, and evaluate 30 reviewer configurations, finding that low rewrite sensitivity often coincides with score collapse across papers ('false robustness') and that human alignment ranks reviewers differently; they then introduce SciCore, a dual-branch reviewer that averages a full-manuscript judgment with a judgment based on an extracted structured science core, achieving a leading joint stability-discrimination profile in the primary GPT-5.5 comparison (ICC 0.775, SPR 0.652, discriminability 0.
The work introduces Symbolic Closure Analysis (SCA) to characterize exploration bias and compounding bias in long-horizon reasoning, and builds SAGE, a framework that injects structural priors during post-training via algebraic sparsification and hyperbolic structural guidance, outperforming SFT, GRPO, EMPO, and GRPO-PRM across 12 benchmarks and 7 model families and achieving up to an 8-fold improvement in Lean-verified proofs on the open Andrews-Curtis task.
You’re all caught up