AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where multi-agent systems with diverse, task-specialized agents complement one another through structured communication and collaboration. Today, coordination is usually handled with imprecise, ad-hoc natural language, which limits complex interaction and hinders interoperability with domain-specific agents. We introduce Agent context protocols (ACPs): a domain- and agent-agnostic family of structured protocols for agent-agent communication, coordination, and error handling. ACPs combine (i) persistent execution blueprints -- explicit dependency graphs that store intermediate agent outputs -- with (ii) standardized message schemas, enabling robust and fault-tolerant multi-agent collective inference. ACP-powered generalist systems reach state-of-the-art performance: 28.3 % accuracy on AssistantBench for long-horizon web assistance and best-in-class multimodal technical reports, outperforming commercial AI systems in human evaluation. ACPs are highly modular and extensible, allowing practitioners to build top-tier generalist agents quickly.

We investigate a family of inference problems on Markov models, where many sample paths are drawn from a Markov chain and partial information is revealed to an observer who attempts to reconstruct the sample paths. We present algo- rithms and hardness results for several variants of this problem which arise by re- vealing different information to the observer and imposing different requirements for the reconstruction of sample paths. Our algorithms are analogous to the clas- sical Viterbi algorithm for Hidden Markov Models, which finds the single most probable sample path given a sequence of observations. Our work is motivated by an important application in ecology: inferring bird migration paths from a large database of observations.

Collective inference is widely used to improve classification in network datasets. However, despite recent advances in deep learning and the successes of recurrent neural networks (RNNs), researchers have only just recently begun to study how to apply RNNs to heterogeneous graph and network datasets. There has been recent work on using RNNs for unsupervised learning in networks (e.g., graph clustering, node embedding) and for prediction (e.g., link prediction, graph classification), but there has been little work on using RNNs for node-based relational classification tasks. In this paper, we provide an end-to-end learning framework using RNNs for collective inference. Our main insight is to transform a node and its set of neighbors into an unordered sequence (of varying length) and use an LSTM-based RNN to predict the class label as the output of that sequence. We develop a collective inference method, which we refer to as Deep Collective Inference (DCI), that uses semi-supervised learning in partially-labeled networks and two label distribution correction mechanisms for imbalanced classes. We compare to several alternative methods on seven network datasets. DCI achieves up to a 12% reduction in error compared to the best alternative and a 25% reduction in error on average — over all methods, for all label proportions.

Gradient boosting of regression trees is a competitive procedure for learning predictive models of continuous data that fits the data with an additive non-parametric model. The classic version of gradient boosting assumes that the data is independent and identically distributed. However, relational data with interdependent, linked instances is now common and the dependencies in such data can be exploited to improve predictive performance. Collective inference is one approach to exploit relational correlation patterns and significantly reduce classification error. However, much of the work on collective learning and inference has focused on discrete prediction tasks rather than continuous. %target values has not got that attention in terms of collective inference. In this work, we investigate how to combine these two paradigms together to improve regression in relational domains. Specifically, we propose a boosting algorithm for learning a collective inference model that predicts a continuous target variable. In the algorithm, we learn a basic relational model, collectively infer the target values, and then iteratively learn relational models to predict the residuals. We evaluate our proposed algorithm on a real network dataset and show that it outperforms alternative boosting methods. However, our investigation also revealed that the relational features interact together to produce better predictions.

The challenge of using communications infrastructure to stabilize other infrastructures is related to research on the collective communications systems in social animals, robots, and human-non-human interaction. In these systems, voting models can explicate patterns of observed behavior or predict collective outcomes. Developing more theoretical deductive explanatory power can increase our knowledge about the interplay of voters and communication that produces collective inferences. This paper suggests that many analyses of voting patterns have not integrated what is known about the predictive properties of voting processes into their analyses. Taking a more deductive approach enables us to think about the strengths and weaknesses of existing explanations and imagine new types of analysis that have implications for engineering communications systems to stabilize other infrastructures.

We consider the problem of jointly training structured models for extraction from sources whose instances enjoy partial overlap. This has important applications like user-driven ad-hoc information extraction on the web. Such applications present new challenges in terms of the number of sources and their arbitrary pattern of overlap not seen by earlier collective training schemes applied on two sources. We present an agreement-based learning framework and alternatives within it to trade-off tractability, robustness to noise, and extent of agreement. We provide a principled scheme to discover low-noise agreement sets in unlabeled data across the sources. Through extensive experiments over 58 real datasets, we establish that our method of additively rewarding agreement over maximal segments of text provides the best trade-offs, and also scores over alternatives such as collective inference, staged training, and multi-view learning.

Collective graphical models exploit inter-instance associative dependence to output more accurate labelings. However existing models support very limited kind of associativity which restricts accuracy gains. This paper makes two major contributions. First, we propose a general collective inference framework that biases data instances to agree on a set of {\em properties} of their labelings. Agreement is encouraged through symmetric clique potentials. We show that rich properties leads to bigger gains, and present a systematic inference procedure for a large class of such properties. The procedure performs message passing on the cluster graph, where property-aware messages are computed with cluster specific algorithms. This provides an inference-only solution for domain adaptation. Our experiments on bibliographic information extraction illustrate significant test error reduction over unseen domains. Our second major contribution consists of algorithms for computing outgoing messages from clique clusters with symmetric clique potentials. Our algorithms are exact for arbitrary symmetric potentials on binary labels and for max-like and majority-like potentials on multiple labels. For majority potentials, we also provide an efficient Lagrangian Relaxation based algorithm that compares favorably with the exact algorithm. We present a 13/15-approximation algorithm for the NP-hard Potts potential, with runtime sub-quadratic in the clique size. In contrast, the best known previous guarantee for graphs with Potts potentials is only 1/2. We empirically show that our method for Potts potentials is an order of magnitude faster than the best alternatives, and our Lagrangian Relaxation based algorithm for majority potentials beats the best applicable heuristic -- ICM.

We investigate a family of inference problems on Markov models, where many sample paths are drawn from a Markov chain and partial information is revealed to an observer who attempts to reconstruct the sample paths. We present algorithms and hardness results for several variants of this problem which arise by revealing different information to the observer and imposing different requirements for the reconstruction of sample paths. Our algorithms are analogous to the classical Viterbi algorithm for Hidden Markov Models, which finds the single most probable sample path given a sequence of observations. Our work is motivated by an important application in ecology: inferring bird migration paths from a large database of observations.

We investigate a family of inference problems on Markov models, where many sample paths are drawn from a Markov chain and partial information is revealed to an observer who attempts to reconstruct the sample paths. We present algorithms and hardness results for several variants of this problem which arise by revealing different information to the observer and imposing different requirements for the reconstruction of sample paths. Our algorithms are analogous to the classical Viterbi algorithm for Hidden Markov Models, which finds the single most probable sample path given a sequence of observations. Our work is motivated by an important application in ecology: inferring bird migration paths from a large database of observations.

We investigate a family of inference problems on Markov models, where many sample paths are drawn from a Markov chain and partial information is revealed to an observer who attempts to reconstruct the sample paths. We present algorithms andhardness results for several variants of this problem which arise by revealing differentinformation to the observer and imposing different requirements for the reconstruction of sample paths. Our algorithms are analogous to the classical Viterbialgorithm for Hidden Markov Models, which finds the single most probable sample path given a sequence of observations. Our work is motivated by an important application in ecology: inferring bird migration paths from a large database of observations.