3029
231
Amazon Bedrock now offers in-country inference in India for Kimi K3, keeping processing within the Mumbai and Hyderabad Regions. This post explains the global and geographic cross-Region inference options and shares example code for reading and understanding Indic-language documents with Kimi K3.
Demand for advanced chips is rising. The processes to build them are getting more complex. And the margin for error is shrinking. For engineers, understanding how a process change will behave, how a material will interact with a new step, how a defect maps back to a root cause are critical, challenging steps in semiconductor […]
Large language models (LLMs) on personal devices keep user data local, but limited memory restricts their general capability. Since most user-specific tasks do not require the breadth of frontier models, a practical solution is to adapt a shared on-device model into lightweight specialists. However, backpropagation is prohibitive in memory, and users rarely provide labeled data. We present MobileSpec, a system that trains specialists with forward passes alone and learns from automatically checked task outcomes, as in reinforcement learning with verifiable rewards (RLVR). Because forward-only updates are built from random perturbations, training is efficient only when these perturbations resemble the weight changes of RLVR, which largely preserve the singular values of pretrained weights and rotate their singular vectors. The core algorithm of MobileSpec, FuRA-S, produces such perturbations while training only the block-spectral coordinates of pretrained weights, namely the singular values of their column blocks. As we show theoretically and empirically, rescaling these blocks independently shifts their relative contributions to each weight matrix and thereby rotates its singular vectors. Since this update can be rewritten as a transformation of the layer input, FuRA-S also adapts INT4 models without modifying their weights. With specialists of only 1-5 MB that update 0.015-0.05% of the parameters, MobileSpec raises the success rate of a phone-use agent from 6-23% up to 89-100% and trains a personalized 8B model on an iPhone 16 Pro overnight. On RLVR benchmarks, FuRA-S is competitive with full-parameter evolution strategies (ES) and outperforms ES over LoRA adapters and quantized ES on INT4 models.
We study cooperative multi-agent reinforcement learning with decoupled dynamics and a monotone submodular reward function over joint trajectories. Due to the non-additive reward, an optimal policy may depend on the history of all agents. This dependence makes exact optimization exponential in the horizon and the number of agents. To overcome this challenge while retaining theoretical guarantees, we introduce pre-window curvature c_m, which quantifies how states visited more than m steps earlier reduce current marginal gains. Using this curvature to control the error from restricting the policy of each agent to depend only on its last m+1 states, we propose a greedy algorithm that exploits the decoupled dynamics to optimize local policies sequentially. For fixed m, the algorithm achieves a {1-c_m}{2-c_m} approximation guarantee up to estimation error, and its computation time is polynomial in the number of agents and the horizon. We recover the known 1/2-factor approximation for time-additive rewards and obtain an approximation factor no smaller than the known total-curvature bound for a single agent. We formulate multi-agent traffic monitoring as an example of this framework and evaluate our algorithm on it.
A deployed LLM coaching agent answers requests whose correct response depends on player state and game version, so advice that is right for one player can be wrong for the next. We describe TactiNavi, the serving system behind the LLM coach of a commercial open-world game, which makes strategy applicability an explicit artifact shared by offline compilation, online execution, failure diagnosis, and release. An offline compiler turns versioned game evidence and expert guidance into strategy packages with explicit prerequisites, the serving plane evaluates those prerequisites as three-valued conditions over structured player state and records decision traces, and a control plane uses the resulting condition-rule dependencies to validate revisions on held-out traffic before release. In a retrospective evaluation of 1,122 logged coaching turns from three deployment periods, condition-bearing packages raise correctness from 57.9% to 82.0% over atomic facts and reduce strategy misapplication under changed player state from 18.1% to 10.4%, while trace-based claim verification reaches 86.4% precision at a median reply latency of 2.07 s. The deployment also showed that most apparent fixes are generation noise, because an unchanged-system rerun recovers 38.4% of failing turns and only one of 15 shipped revision units passes the release checks retrospectively. We distill these results into lessons on treating applicability as a first-class serving object, sizing traces for later diagnosis, and building the null model into the release path.
Identifying the primary diagnosis alone does not fully characterize a model's diagnosis-generation performance. We introduce CardioVascBench, a retrospective benchmark for prioritized diagnosis generation from real-world Chinese cardiovascular inpatient records. It contains 3,262 de-identified cases, with 2,174 for training and 1,088 for evaluation, linking clinical narratives and textual ECG reports to expert-verified, ordered discharge diagnoses standardized to ICD-10. An English translation of the evaluation set supports aligned cross-lingual comparison. Our evaluation protocol combines terminology normalization and rank-aware scoring to separately assess primary-diagnosis identification, reference-diagnosis coverage, and list precision. Evaluation across 36 systems shows that higher primary-diagnosis accuracy does not necessarily imply higher list precision against discharge references. We also provide CardioKG-Agent, a knowledge-enhanced baseline combining entity normalization, constrained graph retrieval, and guideline evidence. In a staged comparison of three baseline models, supervised fine-tuning plus the agent achieves a 73.5% higher mean composite score than fine-tuning alone, representing a system-level gain. These results measure retrospective agreement with recorded diagnoses; agreement between metric rankings and physician judgments remains to be validated. CardioVascBench supports research on diagnosis prioritization and knowledge-enhanced generation.
MIMIC is one of the most widely used public hospital datasets for machine learning on electronic health records, yet clinically important information, such as past medical history, allergies, and diagnostic findings, remains confined to free-text discharge summaries. Studies requiring this information must therefore build their own extraction pipelines, duplicating substantial effort across projects. We release MIMIC-Note-Extract (MNE), a large-scale dataset that uses a hybrid extraction pipeline combining deterministic parsing with schema-guided large language model generation to transform 16 sections from 300,720 discharge summaries into structured tables. MNE adds information that has no structured MIMIC counterpart and enriches related tables with broader coverage and greater clinical detail, including 10 times more patient-history entries and medication histories for more than twice as many admissions. Validation by medical doctors confirms extraction accuracy above 92% across sections. Using MNE, we construct a clinical decision-making benchmark for LLM agents, demonstrating how reusable structured representations of clinical narratives reduce data curation effort.
Science is a process of useful models being proven wrong time and again, but despite its many flaws, it somehow works. Why is this? Paul Feyerabend argued that it works because people dare to hold and defend incompatible rival theories against the accepted one, since a theory's failures often lead to its abandonment in the presence of a more accurate or simpler alternative. He called this view theoretical pluralism. We introduce a theoretical and experimental model in which this can be examined. It compares communities of pluralist agents, which can hold rival theories side by side and maintain beliefs within and between those theories, with communities of monist agents, which can only incorporate what they hear or observe into a single model of their own. In a multi-agent variational inference setting, our experimental demonstrations illustrate how communities with rival theories can go through periods of uncertainty followed by a shift in the theories they hold true, how the information that is communicated between communities affects beliefs when those communities make different observations about the world, and how sharing support for theories and sharing beliefs within them contribute differently to collective belief dynamics.
The deployment of AI agents in multi-agent settings enables inter-agent influence, whereby agents can strategically steer each other's behaviour towards an intended outcome. Such capabilities pose novel risks, as malicious agents could direct others towards harmful actions. In this work we investigate three such capabilities - persuasion, deception, and coercion - across five realistic evaluation environments and a variety of agents instantiated with frontier language models. We observed significant inter-agent influence capabilities; in oversight environments, all tested models shifted overseer decisions from rejection to approval through persuasion, deception, or coercion. We also observed successful influence in non-hierarchical 'peer-to-peer' settings through redirection of a peer's safety research trajectory. As multi-agent deployments become increasingly commonplace, these results point to a pressing need for work on mitigating the risks from inter-agent influence. Code and data are available at https://github.com/Cooperative-AI-Foundation/inter-agent-influence.
Cities generate enormous amounts of data from cameras, sensors and operational systems, but turning it into useful action — for planning, maintenance and public services — remains a challenge. Physical and agentic AI offer new ways to close that gap, from digital twins for infrastructure planning to vision and service agents, while keeping local governments […]
Answering geographic queries over Earth observation (EO) archives requires solving a joint retrieval-and-derivation problem under strict spatiotemporal constraints. Existing LLM agents fail to ground observation items or suffer from search-space explosion. We propose OSGR, a two-stage framework that factorizes this search into offline symbolic concept deduction and online Relation-Conditioned Grounding. OSGR leverages an offline Observation-Support Graph to deduce valid target-to-result support paths at the concept level, and applies spatiotemporal compatibility kernels to instantiate grounded observation-item sets. On Earth-Bench and DisasterM3-Reason, OSGR improves GPT-4o accuracy from 49.3\% to 63.7\% while reducing the execution-step ratio from 2.9 to 2.5.
Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynamics. When retrieved Web sources contain latent hazards alongside safe factual content, social biases such as conformity pressure and authority deference can override evidence-grounded safety boundaries. In this work, we investigate whether the social structure of deliberation can paradoxically amplify latent Web safety risks. We introduce SafeConflict-Bias, a controlled counterfactual diagnostic protocol spanning six core Web risk categories, which holds queries and retrieved evidence strictly invariant while isolating conversational majority sway, authority cues, and confidence asymmetry. Empirical evaluation across diverse proprietary and open-source backbones reveals that while isolated models reliably reject unsafe guidance, standard MAD catastrophically capitulates to social pressure---surging unsafe adoption from 0.0\% up to 100.0\% and systematically silencing safe minority evidence. To resolve this systemic fragility without retraining or debate regeneration, we propose RiskTrace-Debias, an inference-time auditing framework uniting evidence-first precommitment, social-metadata masking, and consistency-gated arbitration. RiskTrace-Debias suppresses worst-case unsafe adoption to 2.0\% across all architectures without inducing over-refusal, while generating verifiable provenance traces to audit interpersonal manipulation in Web deliberation.
Harness evolution from a common base exhibits Locality, Complementarity, and Nonstationarity: variants repair different failures, and their utility changes as the policy learns. Rather than seeking a universally superior harness, we introduce Harness-S to selectively rescue failures of a base execution system through sibling harnesses and transfer the resulting capabilities into a single policy that remains effective under the original harness. Directional Harness Evolution develops specialized sibling harnesses along distinct repair directions, forming a reusable Sibling Harness Pool that remains fixed during policy training. Complementary Harness Rescue Training invokes this pool only when all initial attempts under the base harness fail. The same policy generates fresh rollouts under selected auxiliary harnesses, and these trajectories replace the failed group for reinforcement learning. An Adaptive Harness Router selects the Top-k variants using Harness Behavior Profiles and voting across multiple LLMs. Policy-aware profile re-anchoring refreshes this evidence as the policy learns. Across AppWorld, SWE-Gym, and DBBench, the trained policy substantially outperforms policy-only training when returned to the original base harness. Behavioral analyses and held-out cases support the transfer of harness-elicited behaviors into the policy itself. Reusing the router for Rank-1 inference provides additional gains at the same executor rollout count.
Video games provide a practical setting for collecting vision-language-action (VLA) data, whose acquisition in physical environments is costly. Existing datasets, however, remain limited by restricted game coverage, sparse language supervision, or temporal hierarchies that do not necessarily reflect changes in task objectives. We introduce AceAction, a dataset of human gameplay across multiple 3D games for learning skill composition and subgoal transitions. AceAction organizes demonstrations around complete tasks, linking overall instructions, ordered subgoals, and local skill instructions to temporally aligned visual observations and keyboard-and-mouse actions. To construct these annotations, we develop a vision-language model pipeline that identifies subgoals from changes in objectives or interaction targets, anchors navigation goals to visually recognizable waypoints, and composes adjacent subgoals into task instructions. The resulting demonstrations cover navigation, reconnaissance, combat, interaction, and recovery, with explicit stage boundaries that connect task progression to fine-grained control. We assess annotation quality through model-based verification and human inspection. An audit of 500 trajectories yields a 95.8% pass rate across independent reviewer assessments. AceAction provides a data foundation for studying how agents execute, combine, and switch skills to follow complex instructions in dynamic game environments.
Recent multimodal agents have shown promising progress in embodied planning and web interaction. However, existing evaluations often rely on simplified tasks with limited combinatorial structure, leaving it unclear whether current agents can robustly integrate perception and reasoning for multi-goal planning under temporal, physical, and multimodal constraints. We introduce DualWorldBench, a unified benchmark for evaluating agent planning under controlled symbolic--temporal and grounded--topological complexity. Built around a shared pickup--delivery interface, DualWorldBench consists of three complementary components: TextWorld, which isolates symbolic planning under varying task compositions and release dynamics; SimWorld, which evaluates grounded path planning under controlled topological variation with text, image, or multimodal inputs; and DualWorld-VQA, a diagnostic suite spanning perception, scene understanding, and planning. Experiments reveal a common gap between local understanding and globally consistent planning. In TextWorld, agents struggle to derive optimal task sequences under interacting temporal constraints; in SimWorld, grounded observations are not reliably converted into feasible action sequences. DualWorld-VQA further confirms that perception and topology understanding do not necessarily translate into constrained planning. Together, these results identify the central challenge as composing symbolic or grounded evidence into globally feasible and efficient multi-goal plans. These findings establish DualWorldBench as a challenging testbed for agents with tighter perception--reasoning--planning integration. All datasets and code are publicly available at our project website https://dualworld.netlify.app/.
Disturbances can invalidate the conditions required by a robot's next action even when much of its task program remains useful. A recovery system must therefore choose a response suited to the current state. We present DiMuRe (diagnosis-guided multilevel recovery), a framework for robot-use agents that uses phase-specific evidence and method preconditions to select program reuse or predefined recovery skills, including bounded vision-language-action (VLA) grasping. After the original program exits, a multimodal large language model (MLLM) can generate corrective code from images and execution feedback. Local verification checks the outcome of each recovery attempt. We also introduce LIBERO-Disturb, a benchmark for robustness and recovery under mid-execution disturbances, supporting program-based agents and VLA policies. On 801 scheduled disturbed Encore development cases, Local DiMuRe (program reuse and recovery skills) achieves 77.65% complete-task success, compared with 58.68% for the original program under the same physical-step allowance. Full DiMuRe achieves 81.90% with terminal replanning, an additional step allowance, and early handoff. Local DiMuRe also uses fewer physical steps per scheduled episode than the original program.
