DSA is presented, an evidence-aware orchestration framework for multi-market stock research with large language model (LLM) agents that establishes implementation conformance for the tested software contracts, not superior report quality, forecasting accuracy, or investment returns.
Abstract
Large language models can summarize financial information, but an operational stock-research system must first assemble heterogeneous evidence, expose unavailable data and model capabilities, and control how generated opinions affect a final report. We present DSA, an evidence-aware orchestration framework for multi-market stock research with large language model (LLM) agents. DSA organizes the workflow into evidence acquisition, structured context construction, model-routed analysis, optional role and Strategy Skill reasoning, and report generation with selected context and diagnostics. A default report profile and an optional agentic profile share evidence and model-routing services but use profile-specific output validation and risk safeguards. In the agentic profile, core role outputs are processed by role-specific parsers, whereas Strategy Skill opinions undergo an additional signal-eligibility partition before synthesis; disagreement is supplied explicitly to the decision agent, followed by a conservative risk override. The reference implementation includes six regional market paths, fifteen bundled Strategy Skills, hosted and local model routes, and multiple execution and delivery surfaces. At a frozen software snapshot, a selected manifest of 1,457 portable offline backend contract tests passed; 596 cases were retrospectively mapped to six contract families central to the reported LLM-agent architecture. This evidence establishes implementation conformance for the tested software contracts, not superior report quality, forecasting accuracy, or investment returns.
AI-enabled service-oriented systems change through code, data, prompts, service contracts, retrieval indices, and deployment workflows, which makes regression impact difficult to localize with code-centric evidence only. Existing regression test selection methods provide strong code-, configuration-, and service-level signals, but they provide limited guidance on how to reconcile structural, document, semantic, retrieval, and risk evidence when these signals disagree. This paper presents a multi-agent orchestration framework for change impact analysis and budget-aware regression test selection, where specialized agents score various evidence, a coordinator applies a fixed CI/CD budget, and a graph-backed variant records arbitration traces. We evaluate the framework on three case-study systems: an anonymized industrial wellness retrieval-augmented generation (RAG) platform with 300 tests, a microservice application with 150 tests, and a CI/CD pipeline with 60 tests. Each system has six snapshots, producing five evaluated change transitions, with two replicates per transition and the same budget rule across systems. The results are mixed and informative: the base multi-agent configuration is competitive with monolithic fusion, the graph-backed configuration recovers the strongest CI/CD score, and single-signal baselines remain strongest when one impact mechanism dominates. These findings position the multi-agent test selection approach as an observable, configurable decision framework for cross-domain impact analysis rather than a universally superior predictor.
Nariman Mani, Amr S. Abdelfattah, Shakthi Weerasinghe et al.· International Conference on...· 0 citations
As large language model (LLM) agents move from isolated prompting to longhorizon workflows, failures increasingly arise at the role-to-instance binding boundary, where task-specific role requests must be assigned to concrete agent instances under current service, network, and query conditions. Existing agent system research has improved role specialization, workflow topology, memory, and tool use, but often assumes a fixed stable execution environment. This assumption limits deployed reliability, because the same role request can exhibit different latency, failure probability, and output quality across agent instances operating under different service regions and network conditions. We propose Hedged Agent Computing (HACO), a runtime control scheme that treats each role request as a reliability-constrained selection problem over candidate agent instances, each coupling a role type, an LLM, and a concrete execution environment. Different from routing, HACO adaptively selects a hedge set of candidates for each invocation. Its allocation rule combines optimistic ranking, which prioritizes candidates with high estimated quality, reliability, and informative uncertainty, with conservative reliability accumulation, which stops selection only after the hedge set reaches a target success probability. Through experience harvesting, HACO updates candidate and link profiles from all executed candidate traces, including quality, success, latency, and network statistics. Experiments on various benchmarks, together with runtime degradation studies, show that HACO improves robustness and output quality under changing deployment conditions, while using lower token and latency cost than exhaustive parallel execution.
Eluna is a graph-guided, multi-agent framework that encodes SOPs as directed acyclic graphs with progressive disclosure and delegates independent tasks to parallel sub-agents, each with persistent code execution and live data access.
Ning Liu, Kalle Kujanpää, Zhaoxuan Zhu et al.· 1 citation
Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over time rather than being fully specified at the initial prompt. Service agents make this challenge especially concrete: users may clarify or revise their goals, while tool responses provide information needed for subsequent decisions. Thus, a final reward alone cannot indicate which actions contributed to resolving the task. Recent methods rely on comparative evidence from other trajectories or resampled continuations, or on separately constructed step-level learning signals, to refine credit. However, a completed rollout already records how information and errors flow between agent actions. We introduce Influence-Aware Policy Optimization (IAPO), which represents each rollout as a typed influence-dependency graph over trainable agent actions, with user and tool observations serving as evidence. IAPO converts support-use and failed-use structure into routing weights that redistribute the same trajectory-level advantage. Experiments with Qwen3-4B and Qwen3-8B demonstrate superior performance over multi-turn reinforcement learning (RL) baselines across three service-agent benchmarks: ${\tau^2}$-Bench, UserBench, and AgentChangeBench. BFCL-v4 Multi-Turn further shows that these gains do not compromise multi-turn function-calling performance. This work advances the understanding of credit assignment in multi-turn user interactions and provides a principled approach to training service agents from sparse outcome feedback.
Production customer-service bots must improve answer quality across iterative releases, yet large language models must not bypass evidence boundaries, policy rules, or human-handoff safeguards. We present an \textbf{Evidence-Grounded Customer-Service Agent Workflow} deployed in a real-world customer-service setting. BM25 recall, issue-title-vector recall, issue-description-vector recall, weighted RRF fusion, and cross-encoder reranking construct grounded FAQ evidence for controlled LLM decisions. Policy-guided orchestration then combines this RAG evidence with scenario-specific rule evidence, conversation memory, and clarification state inside a fixed LangGraph DAG~\cite{langgraph2024}. The paper contributes three reusable deployment patterns: \textbf{hybrid RAG evidence construction}, where multi-channel retrieval and reranking produce auditable FAQ candidates; \textbf{evidence-grounded issue/action decision}, where an Evidence-Grounded Decision Module selects an issue/action from typed FAQ evidence and scenario-specific rule evidence; and \textbf{trace-driven RAG and reranker improvement}, where traces diagnose whether failures come from recall, ranking, final candidate selection, clarification, rule-derived evidence, or action policy, and where reranker fine-tuning is evaluated not only for in-domain gain but also for forgetting risk.
Chunming Wu, Dafei Qiu, Congde Yuan et al.· 0 citations
Existing agentic approaches for recommendation system optimization remain fundamentally reactive: they adjust parameters in response to observed metric changes but lack the ability to proactively design controlled experiments, personalize strategies at the user-segment level, or accumulate reusable experimental methodology across tasks. We present PILOT (Proactive Insight Learner for Online Tree-Experiments), an LLM-agent framework that organizes three roles within a constrained control loop where deterministic services enforce all safety, statistical, and permission boundaries: (1) an Experiment Manager that drives the full experiment lifecycle -- task intake, observation governance, anomaly recovery, and postmortem -- by selecting only from a rule-generated legal-command envelope; (2) a Search Planner that proposes candidate decision trees for user-segment-level personalization, invoked only when the Manager requests planning; and (3) a Memory Curator that asynchronously distills experiment outcomes into strategy-level domain knowledge and provenance-tracked methodology, failure-isolated from the main loop. The Manager makes the agent proactive, the Planner enables population-level personalization beyond global tuning, and the Curator turns every completed task into a learning opportunity for the next. Deployed on Taobao's platform with 5 experimental buckets, PILOT is compared against ROAM(Reactive Optimization with Agent-driven Moves), a free-exploration agent without lifecycle governance or structured hypothesis testing. PILOT achieves up to +1.40% IPV, +1.60% Core IPV, +0.96% transaction count, and +1.50% transaction amount, improving over ROAM's best results (+1.00% IPV, +0.90% Core IPV, +0.60% transaction count, +1.13% transaction amount) while raising search efficiency from 53.3% to 93.3% (+40 pp), with no human intervention throughout the experimental cycle.
Jiuning Lin, Ruiquan Lan, Xiaodong Zhu et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduAug 17, 2026
A USAF cadet and a Lincoln Laboratory researcher found AI chatbots can help nontechnical service members produce viable software applications for their unique problems.
