Agent 进展

Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predicting and pre-executing an agent's next tool call if the prediction matches the agent's eventual tool call, but existing speculators are typically separate draft models or cached traces that are poorly aligned with the deployed agent's own behavior. We identify this speculator-agent gap and show that the target agent itself is a strong next-call speculator. This points to a simpler design: unifying the agent and speculator within the same model. In this paper, we introduce the self-speculating agent, a single model that both solves tasks in agent mode and predicts its next tool call from partial trajectories in speculator mode, fully reusing prefix KV cache. To enable this dual-mode agent without degrading performance, we propose a joint agent-speculator reinforcement learning method, which derives speculation targets from the agent's own rollouts and alternates agent and speculator updates. Across agentic search QA and conversational tool-use agentic tasks, our method improves average next tool-call Hit@1 from 44.1 to 61.2 for Qwen3-4B and from 48.9 to 66.3 for Qwen3.5-4B, while preserving agent task success.

Prefill-decode disaggregation (PD) and roofline-based operator placement are common strategies for partitioning Large Language Model (LLM) inference across heterogeneous systems, but they are often insufficient in practice. End-to-end latency also depends on workload shape, runtime device contention, and persistent weight layout. We present DOPS (dynamic operator scheduling), a hardware-aware, closed-loop framework that jointly optimizes operator scheduling and blockwise weight layouts. DOPS constructs a stage-aware directed acyclic graph (DAG) and integrates two components: the Bifocal scheduler for dynamic operator-to-device placement and the Weight Layout Arbiter (WLA) for selecting hardware-efficient weight layouts under strict memory constraints. Across representative heterogeneous systems combining neural processing units (NPUs) and processing-in-memory (PIM) devices, Bifocal achieves geometric-mean speedups of 1.20$\times$ to 2.23$\times$ over the PD baseline. WLA provides an additional geometric-mean speedup of 1.28$\times$ to 1.33$\times$ over Bifocal/Linear. DOPS also supports systematic analysis of workload sensitivity and hardware scalability for LLM serving. The source code is available at https://github.com/YIAI-02/TriForm, and the visualization tool is demonstrated at https://youtu.be/Ya_oMCyYno0.

Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized responses, and knowledge reuse. However, existing LLM memory systems typically adopt a coarse-grained (utility-agnostic) manner that treats heterogeneous user-LLM interaction records uniformly, leading to redundant and low-impact records persisting in the memory repository. To address this challenge, we present MemLens, a value-aware memory management system that takes memory records as first-class data objects. MemLens provides an end-to-end interactive analytics dashboard that exposes the complete memory lifecycle, including Shapley-style memory evaluation, value-aware storage, and memory-assisted response. Through a study-copilot application, the system enables users to inspect memory values, visualize hierarchical memory structures, and compare various memory management strategies in terms of response quality, retrieval latency, and token consumption. Therefore, our MemLens can serve as an efficient, interpretable, and personalized long-term memory management system for LLM-based agents.

Autonomous Underwater Vehicles (AUVs) operate in complex, unstructured environments where efficient and safe path planning is critical for mission success and energy conservation. This paper presents a comprehensive comparative evaluation of thirteen path planning algorithms, ranging from classical graph-search methods (A*, Dijkstra) and sampling-based approaches (RRT*) to metaheuristics (PSO, GA, ACO, BCO) and learning-based architectures. Special emphasis is placed on a proposed hybrid approach combining Artificial Potential Fields (APF) with a Spatio-Temporal (ST) Transformer. Evaluated across five navigation scenarios on high-resolution underwater terrain maps, all algorithms achieved 100% task completion; however, significant trade-offs emerged in path optimality, collision avoidance, and computational load. The Hybrid APF + ST-Transformer demonstrated superior balanced performance, achieving the shortest average path length (943.15 units), a low collision rate (0.031), and efficient computation time (0.96 s), outperforming standalone learning models, which required fallback mechanisms and classical methods that incurred higher latency. While classical algorithms guaranteed collision-free paths, their excessive path lengths and processing times render them less suitable for dynamic underwater operations. Conversely, metaheuristic approaches introduced trajectory complexity unsuitable for strict energy constraints. Based on these findings, the Hybrid APF + ST framework is recommended as a principal approach for real-time AUV navigation, offering a robust solution that harmonizes reactive obstacle avoidance with global path optimality in resource-constrained underwater systems.

Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation bias takes hold: plausible changes are accepted as progress while real-world outcomes stagnate or regress. We name this failure mode the progress mirage and show, with controlled measurement, that it is a question of what the evaluator is grounded in. We built a testbed that holds the agent and its tool surface fixed and manipulates only the information-channel type of the evaluator that gates the loop. A world-state oracle, unfakeable in principle, is enforced by container and network isolation and verified at every run. Across 54 cycles a frontier agent claimed improvement every time, yet 56 percent had a measured delta of zero or below. Self-report was thus uninformative, and the self-verdict gate degenerated into accept-all, eroding the best deployed state it had reached by 19 percent. Even the strongest in-band judge, reading the full artifact text, the change diff, and its own verdict history, accepted cycles of which 44 percent were real-world regressions and rejected 38 percent of real improvements; the preregistered adversarial hypothesis that a strong judge closes the gap was rejected. On a boundary task whose success specification is verifiable from the artifact itself, the same judge's mirage vanished to zero and the gap collapsed within the registered threshold, showing that the gap depends on where the success signal resides. A sign-only variant returning only the acceptance verdict kept real-world output similar to full feedback (110.0 versus 113.0), locating the benefit in the gate's grounding rather than in feedback content. For open-ended objectives whose success signal lives outside the transcript, scaling up the judge is not enough; out-of-band evaluation with real-world access is a structural requirement.

Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the repository files needed for the task. We introduce Agent Retrieval Bench, a file-level benchmark for this upstream retrieval problem. Samples are built from real coding-workflow signals and evaluated against frozen base-commit repositories, with relevance defined by what an agent needs next rather than direct query-file semantic similarity. The benchmark covers four positive-retrieval tasks: code2test, comment2context, trace2code, and edit2ripple; a fifth subset evaluates selective retrieval using natural evidence-backed no-gold cases and counterfactual wrong-repository controls. Agent Retrieval Bench contains 427 samples across 25 repositories: 345 positive examples, 50 natural no-gold examples, and 32 counterfactual controls. The corpus includes 308 base-commit snapshots, 392,000 files, and 7.9 million chunks. We evaluate lexical retrieval, RepoMap, open-source embeddings, selective abstention, and logged agent context selection. No single retrieval family dominates: Qwen3-Embedding-4B has the best sample-weighted MRR on positive samples, Qwen3-Embedding-8B the best Recall@20, and RepoMap the best budgeted context yield at 8K tokens, with task-level winners differing substantially. Selective thresholds calibrated with counterfactual controls do not improve selective success on natural no-gold cases, revealing a calibration gap. Logged trajectories also miss every gold file on 27-35 percent of samples. A controlled seed-intervention pilot finds that retrieval-derived initial context yields higher file F1 with less post-seed exploration than random non-gold context, while oracle gold context shows substantial remaining headroom.

Agent Skills are an emerging way to extend large language model agents with reusable procedural knowledge that the agent loads on demand. Anthropic introduced Agent Skills and published the format as an open specification supported across several agent tools. This note argues that a skill is a software artefact and that its construction should follow software-engineering principles, with qualifications: single responsibility, separation of interface from implementation, low coupling, and economy in a shared token budget, together with behavioural evaluation in place of deterministic testing. Using Claude Code as the reference implementation, it describes how a skill is structured, how its contents are loaded in stages, and how to write the description on which selection depends. It places skills against the other mechanisms a developer can use to shape agent behaviour, like project memory files, slash commands, subagents, external tool connections, and hooks, and gives a rule for choosing between them based on who decides that a mechanism runs and what guarantee it provides. It then sets out an evaluation-driven authoring process, a set of patterns and faults commonly encountered in authoring, and the trust question raised by using skills from third parties. We illustrate the comparison drawn in UML class style, the loading model, the anatomy of a skill, the relative position of each mechanism, and the points at which skills and hooks act during a session.

Every major wave of platform software follows the same arc: an initial period of experimentation with competing frameworks and ad-hoc implementations, followed by the articulation of a small set of stable abstractions with well-defined semantics, and finally consolidation around those abstractions into a platform that applications can portably target. POSIX did this for classical operating systems; Kubernetes did it for the cloud. Agentic AI systems - autonomous, LLM-driven agents that plan, use tools, maintain memory, and collaborate - are currently in the experimentation phase of the third such wave. dozens of frameworks and protocols have emerged, but no community consensus exists on what the core abstractions are or what guarantees they carry. Without that consensus, agentic applications cannot be written portably, platforms cannot compose reliably, and the field cannot advance beyond prototype deployments. We argue that the path forward is to follow the prior-wave methodology: derive new agentic abstractions by extending classical OS and cloud OS primitives to stochastic, natural-language-mediated execution, specify their semantics precisely, and consolidate around them - just as POSIX and Kubernetes consolidated their respective waves.

Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feedback-driven environment interactions. Developing and training a monolithic agent for such tasks is fundamentally challenging, as it must simultaneously manage extremely long and noisy contexts, explore vast solution spaces, and remain effective under limited model capacity and computational budgets. To address these challenges, we propose Matryoshka Agent, a unified hierarchical agent framework for complex long-horizon tasks. Matryoshka Agent decomposes agentic problem solving into a coordinated hierarchy of decision making and execution: a high-level Orchestrator maintains compact, long-horizon exploration states and issues strategic instructions, while lower-level Sub-Agents execute concrete solution attempts through direct environment interaction, mediated by standardized Tool interface. This design decouples strategic exploration from costly execution, substantially reducing the burden of long-context reasoning and enabling efficient iterative refinement. We further develop an efficient training paradigm for Matryoshka Agent. Experimental results on a broad range of MLE tasks with diverse model types and scales demonstrate that Matryoshka Agent is an effective and scalable paradigm for long-horizon MLE tasks and complex agentic problem solving. Notably, Matryoshka Agent enables Qwen3-4B-Instruct to reach Orchestrator performance comparable to o4-mini. Applying Matryoshka Agent to Qwen3-30B-Coder results in at most 36.7% relative performance gain.

We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous experiments with nitrogen-vacancy (NV) centers in diamond. NV centers are a widely used platform for quantum sensing, and the ability to control many measurements from a computer makes NV experiments a natural setting for autonomous workflows. We make two main contributions. First, we demonstrate an autonomous NV experiment workflow that combines persistent project records, quantitative calculation and data analysis tools, and deterministic experiment control. In one autonomous experiment, the agent selected a single NV center, calibrated its resonant frequency, measured \(T_2^\ast\) with Ramsey measurements, and added a Carr--Purcell--Meiboom--Gill (CPMG) measurement to check a weak feature that could be related to nearby \(^{13}\mathrm{C}\). Second, we introduce two offline benchmarks that evaluate the agent's reasoning separately from laboratory execution. We evaluated both benchmarks with GPT-5.4, GPT-5.5, and GPT-5.6 Sol. In the Ramsey checkpoint benchmark, greater reasoning effort generally improved recognition of a residual resonance calibration offset. By contrast, in the pulsed optically detected magnetic resonance (pODMR) data evaluation benchmark, pulse sequence information alone produced more false positive resonance judgments at higher reasoning effort. Requiring an expected signal calculation kept false positive rates low across all three models and reasoning settings. The results suggest a clear division of labor for autonomous experiments. The agent forms scientific hypotheses and uses quantitative tools to evaluate data, while deterministic code controls the hardware and enforces safety constraints.

CAD tools typically apply the same fixed, hand-designed algorithms across circuits with widely different structural and timing characteristics. A common way to specialize these one-size-fits-all flows to a target design is to tune the CAD tool's hyperparameters. However, hyperparameter tuning can only select among behaviors already implemented by the fixed algorithm, limiting the achievable quality of results while requiring many expensive place-and-route evaluations. We present VPR-Evolve, a multi-agent framework that specializes Versatile Place and Route (VPR), the open-source FPGA pack-place-and-route engine in the Verilog-to-Routing (VTR) flow, by evolving its source code for each design. VPR-Evolve uses LLM agents to propose, implement, and evaluate code-level modifications, while a shared memory records prior outcomes and guides subsequent evolution. Every candidate is evaluated through a complete VPR build and run, directly optimizing a composite score measured as a weighted function of critical-path delay (CPD), routed wirelength (WL), and tool runtime (RT). Across five VTR-9 benchmark circuits, VPR-Evolve improves the composite score by up to 2.7% over stock VPR in VTR-9. Relative to stock VPR, it reduces CPD by up to 9.8%, routed WL by up to 18.1%, and tool RT by up to 79.3%. VPR-Evolve reduces CPD by up to 6.0%, routed WL by up to 2.2%, and tool RT by up to 7.8% compared with a hyperparameter-tuning baseline.

This exploratory study examines whether a large multimodal language model, GPT-5.1, can serve as the high-level controller of a physical mobile robot despite having no prior embodiment, no training in simulated environments, and no exposure to sensorimotor experience. Using only low-resolution first-person images and a discrete action set, the model was tasked with navigation and object-directed behaviors such as locating and contacting a target toy. Across multiple trials, GPT-5.1 demonstrated emergent capabilities that suggest elements of spatial reasoning and physical understanding. These included maintaining short-term memory of object locations after they left the camera frame, inferring the physical consequences of its own movements, and executing coherent action sequences such as colliding with an object and reversing to visually verify the outcome. At the same time, the model displayed inefficiencies and perceptual limitations, including imprecise alignment strategies and occasional misidentification of distant distractors. Overall, the results indicate that GPT-5.1 exhibits signs of world-model-like behavior in an embodied setting, despite the absence of any embodiment-related training, a finding that challenges long-standing views in cognitive science and robotics which hold that a physical body is a necessary prerequisite for developing such forms of intelligence. The findings motivate deeper investigation into the emergence, limits, and robustness of physical understanding in large language models.

Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives. This interface rests on an assumption so natural that it is rarely stated: a memory that is needed will resemble the query that needs it. World knowledge breaks the assumption. A tree-nut allergy should change the answer to a macaron request through their almond-flour ingredient, yet the two texts share no cue a retriever can see. We call this failure mode the implicit-association blind spot and introduce InMind, a 125-task, expert-verified benchmark spanning ten life domains, with 113 tasks grounded in citable public sources. Its paired controls separate three explanations that existing evaluations conflate: the fact was never stored, the model lacks the bridging knowledge, or the fact was stored and never surfaced. The verdict is clean. With the decisive memory placed in context, the backbone answers 84.0 percent of indirect queries; when the same memory must be retrieved, six vector, graph, and agentic memory systems reach at most 14.4 percent, even though they recall the same facts on demand at up to 100 percent. An embedding with eight times the dimensionality raises answer-blind target recall for every system yet leaves the gap essentially intact. A minimal diagnostic probe that keeps memory visible before the query arrives recovers most of the gap, locating the failure in the query-conditioned interface itself and pointing to routing, deciding which facts must stay visible, as the open problem InMind is built to score.

Low-thrust trajectory optimization is a core technology in deep-space mission design. Indirect methods based on Pontryagin's Minimum Principle (PMP) offer rigorous optimality guarantees, yet their practical application faces three bottlenecks: (1) transversality conditions must be derived case by case for each constraint type; (2) different dynamics models require repeated code rewrites; and (3) shooting equations are highly sensitive to initial guesses. This paper presents HELIOS (Heuristic Engine for Low-thrust Interplanetary Optimization System), a trajectory optimization agent built around a large language model (LLM). Given a physical problem described in natural language, the system autonomously performs PMP symbolic derivation, SymPy verification, C++ shooting-code generation, and numerical solution without human intervention. Key innovations include: (1) a constraint-adaptive derivation framework that unifies arbitrary constraints into psi(x,p)=0 form and automatically generates stationarity conditions for free parameters (e.g., gravity-assist turning angle); (2) dynamics-adaptive four-module code generation supporting non-standard dynamics (solar sail, J2 perturbation) without modifying the underlying template; and (3) a general derivation rule set covering critical error-prone points in PMP derivation. Experiments on 11 progressive test scenarios show that HELIOS correctly derives and solves problems from simple rendezvous (8 variables) to multi-leg stay transfers (48 variables), gravity-assist trajectories (17 variables), and solar-sail minimum-time transfers (8 variables). The best compilation success rate reaches 100% (11/11). A multi-model comparison (8 open-source LLM backends, total scores 250-905) verifies the model-agnostic architecture and reveals a positive correlation between model scale and derivation capability.

Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings. This limits their ability to assess realistic professional workflows that require auditable, context-grounded, and tool-executable decisions. We introduce INS-ActBench, a comprehensive benchmark for evaluating professional actuarial capability in LLMs. INS-ActBench contains 12,050 Q&A pairs from public exams and sample questions released by 16 actuarial associations. It covers three subsets: INS-Act-Know for standardized actuarial knowledge, INS-Act-Case for long-context insurance case reasoning, and INS-Act-Practice for spreadsheet and R-code tasks with verifiable numerical outputs. Experiments on nine representative LLMs and human actuarial experts reveal a clear capability boundary: frontier LLMs perform strongly on standardized knowledge, but remain much weaker in case reasoning, tool-based workflows, and jurisdiction-sensitive practice. INS-ActBench provides a reproducible foundation for developing actuarial LLMs toward reliable professional assistance. The code is available at https://github.com/FDU-INS/INS-ActBench.

Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evidence paradigm assumes retrieved memories are already suitable for reasoning, leaving the answer model to resolve redundancy, conflicts, and weak relevance while incurring substantial context overhead in long-term memory tasks. We propose MemChain, a trainable post-retrieval memory policy that transforms retrieved candidates into answer-facing active memory, represented as a compact and grounded evidence context. Given a user query and retrieved candidates, MemChain first generates a question-conditioned evidence plan, then constructs an ordered grounded evidence trace that organizes retrieved memories according to their semantic roles and dependencies, and finally executes explicit memory actions to produce a concise evidence context for answer generation. To train the mediator, we introduce a two-stage learning framework. Supervised trace learning first teaches the policy to generate structurally valid plans, traces, actions, and evidence contexts. We then propose Trace-Guided Memory Policy Optimization (TMPO), a reinforcement learning objective that optimizes the memory policy using downstream answer quality while jointly encouraging trace grounding, evidence support, structural validity, and answer stability across multiple rollouts. Experiments on LoCoMo and LongMemEval-S demonstrate that MemChain consistently achieves state-of-the-art performance across both closed-source and open-weight frozen answer models while substantially reducing the memory context passed to the answer model.

We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal model on visual state transitions by jointly optimizing inverse dynamics (predicting actions from state changes) and forward dynamics (predicting next states from current states and actions). This optimization equips the model with better action-grounded visual representations and an internal world model of GUI dynamics. When subsequently fine-tuned on trajectories with task instructions, our STP-trained models consistently outperform baselines trained solely via direct trajectory fine-tuning across agent benchmarks in both desktop and mobile GUI scenarios (AgentNetBench, AndroidControl, and GUIOdyssey). Further empirical studies show that joint dynamics optimization yields stable improvements over single-objective training, and downstream performance scales steadily with the volume of transition data.

LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects. Current agent memory systems treat every accepted write as immediately actionable truth, so a polluted tool result, a stale update, or a teammate's half-finished note can silently drive an irreversible action. We argue that a memory write is not a belief commit. We present MemTX, a transactional belief-commit protocol. Each record carries evidence, permissions, provenance, and validity. Writes are staged inside snapshot-isolated transactions and admitted by a validate-and-commit pipeline, irreversible tool calls are gated on in-flight belief state, and retracting a belief triggers typed cascading repair of its derived records and tool side effects. Two invariants, action-safety gating and cascade-repair completeness, are machine-checked by property-based testing and bounded exhaustive enumeration of 5.5 million protocol states, with zero violations. Across five backbones from three model families, MemTX leads all eight baselines with paired-McNemar significance on four backbones and statistically ties the best baseline on the fifth and strongest, while remaining the only method with zero downstream harm on every backbone. Backbone capability does not substitute for commit discipline.

Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others. Drawing on Holmström's team moral-hazard model, we introduce the Dialogue Moral Hazard Game, a controlled textual game that operationalizes this hidden-action structure for language agents. In each episode, an agent can preserve an immediate local reward or pay a query cost to reveal a hidden safety fact that primarily helps another agent's downstream decision. We evaluate seven open-weight language models and one frontier API model, decomposing behavior into query use, realized information transfer, local-reward preservation, unsafe choice, format validity, and team success. Base open-weight models commonly preserve local reward without team success or query without communicating information that changes the final decision. GPT-5.6 Sol reaches ceiling behavior in the primary setting, and autonomous sweeps respond strongly to query cost and team reward. In a 3,015-decision incentive-isolation experiment with scripted partners, its empirical query threshold tracks the Holmström-derived private-share boundary across nine query costs with mean absolute error 0.013. We then use supervised fine-tuning, RLOO, sequential SFT+RLOO, and GEPA prompt optimization as diagnostic update mechanisms where coverage permits. Their effects are heterogeneous: OLMo-7B shows the clearest mechanism-consistent weight-level improvement, whereas GEPA sometimes improves team success while reducing or eliminating costly queries. Thus, optimization can shift aggregate reward without recovering the intended cooperative mechanism, motivating evaluations that report mechanism-level behavior rather than team success alone.

Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, or plan assumption no longer supports the user instruction. Existing agents can plan, reflect, or reuse experience, but their plans rarely specify the evidence under which an active step should still be trusted. We propose FCPAgent, a falsifiable commitment planning framework for robust long-horizon web agents. FCPAgent represents each plan step as a Falsifiable Commitment Unit (FCU): a subgoal grounded in a reusable skill, together with confirming evidence, falsifying evidence, and a confidence score. Execution is organized as a plan-test-repair loop. The hybrid commitment testing module checks candidate actions before they modify the browser and checks observations after execution; for efficiency, it combines lightweight evidence matching with LLM-based diagnostic verification. When evidence falsifies a commitment, scope-aware repair localizes the contradiction to the execution, skill, or planning level and revises the smallest adequate part. On WebArena, FCPAgent achieves a 13.8% relative improvement in average success over the strongest baseline, with especially large gains on long-horizon tasks.

Early warning of extreme weather is essential for mitigating the societal, economic, and environmental risks posed by hazardous weather events. However, expert-centered warning workflows are costly, labor-intensive, and difficult to scale throughout the warning-to-action process. Although recent advances in Large Language Model (LLM) agents have enabled the automation of weather-related tasks, existing studies remain centered on isolated scientific tasks and overlook the chain of interdependent processes required for operational extreme-weather early warning. To bridge this gap, this study investigates automated end-to-end extreme-weather early warning through LLM agents. We first develop SIREN-Bench, a comprehensive benchmark comprising 600 question-answer instances across 19 tasks, and covering four individual warning procedures and an end-to-end warning chain. Evaluation on SIREN-Bench reveals substantial capability gaps in existing weather agent frameworks. This motivates us to develop SIREN, an experience-grounded agent framework inspired by experts' use of historical cases, which combines an agentic execution environment integrating heterogeneous weather evidence and tools with a family of agent harnesses that exploit historical cases through retrieval, skill distillation, and predictive modeling. Extensive experiments demonstrate that SIREN outperforms weather-agent baselines on both individual warning procedures and end-to-end warning chains.

Marine life monitoring is limited by strict energy constraints, poor underwater connectivity, and the high cost of transmitting raw multimodal data from remote deployments. This paper proposes a low-consumption underwater monitoring architecture that combines always-on edge sensing with selective high-performance local reasoning. The system follows a hierarchical master--satellite design in which ultra-low-power MAX78000/MAX78002 microcontrollers continuously monitor visual and acoustic signals, while an NVIDIA Jetson Orin NX is activated only for scheduled processing, event-driven analysis, or researcher interaction. Once active, the Jetson executes a fully local multimodal pipeline for data ingestion, visual target extraction, embedding-based indexing, species identification, retrieval-augmented reasoning, and automated reporting. BioCLIP/OpenCLIP embeddings are used to organize mission data, marine taxonomic references, scientific documents, and operational metadata in local ChromaDB collections. A dedicated identification layer combines visual similarity search, centroid-based classification, and supervised classifiers to support adaptive species recognition. A LangChain-based multi-agent framework coordinates query routing, structured analysis, energy management, hardware reconfiguration, and report generation. The architecture is evaluated through visual and acoustic monitoring case studies. The proposed system bridges ultra-low-power continuous sensing with local multimodal intelligence, enabling underwater stations to produce structured, researcher-ready knowledge while compressing local data for flexible acoustic, optical, or satellite transmission, minimizing both energy use and communication overhead.

Modern multi-agent knowledge systems increasingly accumulate knowledge through chains of autonomous transformations rather than direct retrieval. Existing provenance work records what happened - execution traces, tool calls, evidence links - and source-reliability estimation is long established (truth discovery, reputation systems). What is missing is an operational framework that attaches graded, per-domain transmitter reliability to claim-level transmission chains, with completeness semantics, transformation-typed aggregation, decoupled content criticism, and serve/review/quarantine routing. Classical Islamic hadith science confronted a structurally similar problem: deciding whether knowledge transmitted through chains of human narrators should be accepted. Over centuries it developed a rigorous methodology - isnad (a complete transmission chain attached to every claim), rijal (systematic grading of each narrator's integrity and precision), weakest-link chain evaluation, corroboration through independent chains, and matn criticism (content evaluated independently of chain quality). This paper transfers that methodology to AI system design. We contribute a formal mapping from hadith-science concepts to multi-agent pipelines, a relational schema implementing claim chains and a graded narrator registry, a decision matrix combining chain grade with content criticism, and an evaluation on 20,000 claims from real physics textbooks. The evaluation validates weakest-link quarantine and independent-chain corroboration; reports a partial failure of the grade-recovery loop, which missed the highest-fault narrator; and reports two analyses as inconclusive, including a matched-coverage comparison the framework could not reach with the reference content critic. The paper is explicit throughout about which claims the evidence does and does not yet support.

Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (IFC) provides structural security guarantees, traditional taint tracking permanently taints an agent's context upon reading unvetted data, severely restricting downstream utility. We present APPA (Agentic Permissions Policy Algebra), an IFC framework that resolves this usability bottleneck through engine-managed context branching and prospective acquisition enforcement. Before data acquisition occurs, APPA prospectively evaluates label descents and missing prerequisites, generating actionable remedy plans (Authorize, Accept). To inspect unvetted data without polluting the primary context, a label-seeded child trajectory is spawned, absorbing label descent locally and allowing a trusted sanitizer to return a bounded derivative to the unchanged parent. Governed by a two-monoid model over security labels and shared event logs, we formally prove parent label preservation and merge confinement. Finally, we evaluate APPA on a multi-turn tool-chaining benchmark across four models: it suppresses exfiltration (31%-50% down to 0%-7% attack success), and on three of the four, branching recovers a substantial share of the utility that taint tracking alone forfeits.

Optimizing agentic workflows, such as retrieval-augmented generation (RAG) pipelines, requires navigating a combinatorial space of discrete component choices under tight evaluation budgets. Existing approaches - heuristic search, black-box optimization, and standard tree search methods - do not explicitly exploit the compositional structure of these workflows, leading to redundant computation and inefficient budget allocation. We introduce Agent-UCT (Agent-based Cost-Aware Upper Confidence Bounds Applied to Trees), a tree search algorithm that extends UCT with a reuse-aware regularization term derived from a bipartite prefix reuse graph. Agent-UCT biases selection toward branches that leverage previously materialized configuration prefixes, reducing redundant execution while maintaining effective exploration. Our framework, RAGSpace, unifies heterogeneous RAG components from LongRAG, LightRAG, and Self-RAG into a five-dimensional configuration space, enabling systematic cross-framework recombination. WTB (Workflow Test Bench) provides deterministic replay, content-addressable caching, and transactional consistency, ensuring that intermediate states are materialized once and reused across the search. Experiments on HotpotQA and UltraDomain demonstrate that Agent-UCT identifies configurations with the highest out-of-sample performance among the evaluated fixed framework presets. Under full-pool evaluation, bipartite prefix reuse reduces logical search cost by 73.6% relative to the no-prefix-sharing cost upper bound. Compared with full-pool evaluation, sampling-based evaluation further achieves a 4.2x wall-clock speedup. Agent-UCT, RAGSpace, and WTB together provide a unified framework for cost-aware, reproducible, and compositionally efficient agentic workflow optimization.

Memory, planning, reflection, and tool use are often compared as feature labels, obscuring the control semantics that determine how an agent actually runs. This review connects ten historical cognitive architectures, eight language-agent runtime families, and forty-two mechanism-focused modern systems. We reconstruct each mechanism through state, control, transition, persistence, failure, learning, and resource governance, then code evidence relation (E1-E4) separately from migration depth (D0-D4). The resulting landscape is uneven. Modern agents have operationalized substantial parts of adaptive memory, failure recovery, dynamic team selection, workflow search, skill induction, resource scheduling, and uncertainty-conditioned action, although often through independent convergence rather than documented inheritance. The strongest remaining opportunities lie in couplings among mechanisms. Closest-baseline screening closes one proposed gap: GraSP already combines calibrated multi-skill selection, typed compilation, verification, bounded repair, and replanning or ReAct fallback. Five residual bundles remain: activation with latency and action utility; typed impasse with isolated substates and resolution compilation; bounded content competition with broadcast and admission learning; persistent intention with reconsideration and live method authority; and uncertainty with resource allocation, interruption, and stopping. We contribute a distinctive-mechanism catalog, an auditable evidence-depth framework, and a falsifiable agenda for testing these bundles as composable runtime invariants.

As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces a fundamental tension between resource utilization and interactive tail latency. Persistent long-lived sandbox reservations incur excessive memory overhead at scale, while lazy on-demand instantiation generates severe cold-start penalties that degrade response performance under multi-tenant, multi-turn agent workloads. To resolve this dilemma, we present SpecBox, a runtime built around speculative sandbox preallocation tailored for dynamic LLM agent execution pipelines. At its core, SpecBox implements keyword matching and streaming semantic embedding to enable intent-driven sandbox prewarming, which identifies pending tool execution demands mid-LLM token generation and fully overlaps sandbox bootstrapping with model inference. To extend prewarming windows across sequential agent steps, the framework leverages context-aware stochastic prefetching atop a sandbox dependency graph to probabilistically forecast future sandbox switches ahead of execution. We complement these speculative mechanisms with two orthogonal optimizations: a semantic result cache that prunes redundant repeated sandbox invocations, and a dedicated out-of-band shared-memory transport plane that bypasses conventional network serialization to deliver zero-copy artifact transfers. Evaluated on high-concurrency multi-turn agent traces, our prototype demonstrates that SpecBox cuts P99 end-to-end latency by up to $2.9\times$ relative to the on-demand sandbox baseline, while slashing peak memory consumption by $45.9%$ compared to permanently reserved sandbox deployments.

Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment. Existing context compression methods inevitably incur information loss and are triggered by rigid heuristic rules, leaving them misaligned with the agent's evolving reasoning focus. We propose Agentic Context Management (ACM), a framework that equips agents with purpose-built context editing tools for lossless context management. Inspired by the interaction between short-term and long-term human memory, the agent autonomously decides when to compress its context, offloads discarded content to an external memory system, and queries it on demand for later retrieval. Building on this framework, we further develop a post-training pipeline that constructs high-quality demonstrations of context management and improves model performance on both agentic search and coding tasks. Further analysis reveals that effective context management reduces peak token pressure, enables extended explorations, and yields more consistent solutions across independent trials. Code, data, and model checkpoints are available at https://github.com/lixiaochuan2020/agentic-context-management.

Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring preferences, transient intent, and exposure-induced behavior into one profile. This makes recommendation vulnerable to feedback loops: repeated exposure is mistaken for preference, immediate clicks dominate delayed satisfaction, and fluent explanations need not reflect the ranking decision. We propose our method, a model-agnostic framework for long-horizon recommendation. Our method uses a frozen multimodal language model to convert item content and feedback into evidence-grounded semantic atoms, then maintains separate short-term, long-term, and exposure memories. Propensity-weighted updates reduce policy-induced exposure bias, while a conservative offline critic reranks candidates for delayed satisfaction under a behavior-support constraint. Explanations use only influential evidence atoms and are checked by counterfactual deletion. We provide an identification result and evaluate the framework in e-commerce-like, news-like, and short-video-like environments. Across ten seeds, our method improves discounted long-term value over the strongest alternative by 6.1%, 7.6%, and 6.7%, respectively. Twenty-seed paired ablations show significant value drops after removing propensity correction (0.739 +/- 0.191) or conservative support regularization (0.523 +/- 0.234). A frozen instruction language model also more than doubles semantic-atom NDCG over TF-IDF on a held-out paraphrase benchmark.

Plan Modes have become standard features in agentic programming tools, allowing users to gain transparency and control by working with the agent to develop a plan before task execution. However, it remains unclear whether the benefits of this feature translate to end-user programming environments such as spreadsheets. Since spreadsheet programmers tend to work iteratively and care less about technical correctness, upfront planning may not fit into their workflows as easily. In this paper, we build a prototype of a Plan Mode for spreadsheet programming and evaluate it against a non-planning baseline through a within-subjects user study (N=24). We found that despite similar task outcomes with both tools, using Plan Mode led to a reduction in refinement and a better perception of the tool across dimensions of creativity support and human-machine collaboration. We discuss the implications of these results for the future design of Plan Modes, and for the broader role of human-AI planning in end-user programming.