cs.AIOct 20, 2026

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

Authors: Wenjie Lou, Tianshuo Peng, Shiyang Feng, Shengji Tang, Runmin Ma, Ruizhe Chen, Jinxin Shi, Haoyang Peng, 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sage-A1.5 highlights three improvements: agentic orchestration, verification, and open scientific discovery. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently and supporting efficient execution while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing the agent to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We showcase these capabilities through complicated agentic tasks and multidisciplinary scientific applications. Besides, we hope Sage-A1.5 provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.

Figures & tables

Figure 1: Benchmark performance of Sage-A1.5.
Figure 2: Overview of the three-stage training pipeline of Sage-A1.5. First, the model is trained on diverse domain data, including coding, long-context reasoning, deep research, scientific reasoning, and co-working, utilizing environment construction, trajectory selection, staged supervised fine-tuning, and reinforcement learning to build multi-domain teachers. Then, these teachers undergo unified outcome-process post-training to produce the final unified model, which features an agent orchestration for collaborative task solving, iterative agentic verification for reasoning reliability, and local deployment for ensuring data privacy, access control, and offline support.
Figure 3: Two complementary dimensions of agent capability. Capability coverage spans task domains, while capability composition concerns how problem-solving capabilities are organized and adapted during execution. Agentic Orchestration coordinates parallel work and integrates results; Agentic Verification reassesses intermediate responses using available evidence and adjusts subsequent actions.
Figure 4: Agentic Orchestration in execution and task construction. (a) Independently executing subagents return structured feedback for the main agent’s next decisions. (b) Multiple relation chains are built around a selected answer and combined into one question, with identifying details masked. Their clues provide complementary constraints for parallel investigation.
Figure 5: Delegation interface and structured subagent feedback.
Figure 6: Overall framework of the three-stage science-enhanced teacher model training pipeline, comprising capability-guided scientific problem selection, scientific research harness optimization, and trajectory distillation and training to enhance long-horizon scientific research capabilities.
 Comparable Models ( 35B)Larger-scale Models  
 Sage-A1.5Agents-A1Ornith-1.5Kimi-K3GLM-5.3GPT-5.6-sol  
Long-horizon Search        
GAIA [ 28 ]95.196.077.692.292.288.3  
BrowseComp [ 12 ]81.775.567.691.276.290.4  
DeepResearch-Bench2 [ 29 ]43.737.548.652.455.757.9  
XBench-DS-2510 [ 30 ]92.086.080.085.084.090.0  
Table 1: Comparison between Sage-A1.5 and 35B/T-level models. For 35B model, we compare with recently released open-source 35B models. For T-level models, we compare with Kimi-K3 [ 4 ] , GLM-5.3 [ 3 ] , and GPT-5.6-sol [ 5 ] . To ensure a fair comparison, we report the results from their original technical reports. If a model does not report the corresponding benchmark results, we evaluate it using the same evaluation protocol as our model. underline means the best result for 35B parameters, and Bold means the best overall result. Note that GLM-5.3 is text-only and thus not applicable to OmniDocBench.
ModelHLE w/ toolsHiPhOFS-OFS-RCMTCritPt
Qwen3.5-35B-A3B47.437.064.52.520.00.9
Science-enhanced Teacher (SFT)56.849.789.070.084.025.7
Table 2: Performance comparison between Qwen3.5-35B-A3B and the science-enhanced teacher.
ModelGAIABrowseCompDeepResearch Bench IIXBench-DS-2510
Qwen3.5-35B-A3B59.861.042.377.0
Search-enhanced Teacher (SFT)96.185.548.289.0
Table 3: Performance comparison between Qwen3.5-35B-A3B and the search-enhanced teacher.
ModelBrowseCompDeepResearch Bench II
Qwen3.5-35B-A3B61.042.3
Sage-A1.5 w/o Agentic Orchestration81.743.7
Sage-A1.5 w/ Agentic Orchestration82.847.5
Agentic Orchestration Teacher81.653.6
Table 4: Performance of Agentic Orchestration on BrowseComp [ 12 ] and DeepResearch Bench II [ 29 ] . The teacher is evaluated with Agentic Orchestration enabled. Bold denotes the best result in each column.
Model / ModeBrowseCompOutput TokensTurns
Qwen3.5-35B-A3B61.014,85165.22
Agentic Verification teacher (normal mode)81.023,24584.81
Agentic Verification teacher (verify mode)85.521,96282.14
Table 5: Performance and token costs of Agentic Verification on BrowseComp [ 12 ] . Tokens and turns are averaged per task.
ModelMed+GoldSilverBronzeAny Medal
Qwen3.6-35B-A3B62.12±4.0162.12\pm 4.0122.73±2.6222.73\pm 2.627.58±4.017.58\pm 4.017.58±1.527.58\pm 1.5237.88±5.4637.88\pm 5.46
MLE Teacher (SFT+RL)84.85±3.03\mathbf{84.85}\pm 3.0350.00±2.62\mathbf{50.00}\pm 2.6216.67±1.52\mathbf{16.67}\pm 1.526.06±1.526.06\pm 1.5272.73±2.62\mathbf{72.73}\pm 2.62
Table 6: Performance comparison between Qwen3.6-35B-A3B and the MLE teacher on MLE-Bench Lite [ 15 ] . Results are reported as mean ±\pm SEM over three evaluations (%).
Figure 7: Agentic Orchestration in a 50-channel research atlas. Left: the 13-turn main-agent trajectory, with badges marking delegation and batch sizes. Upper right: parallel subagents investigate 50 channels in six successive batches, after which one further subagent examines cross-channel relationships. Lower right: the StarPlus subagent tests the delegated Sony attribution against evidence and corrects it to Disney Star / JioStar ; the main agent uses this correction in its subsequent relationship assignment and final atlas. Task execution time measures the end-to-end elapsed duration; total research time sums the execution durations of all subagents.
Figure 8: Agentic Verification in a multi-hop BrowseComp task. (a) The task identifies an actor’s first wife through clues about film roles, marriages, and family history. (b) Repeated searches fail to establish a reliable candidate. (c) The model autonomously initiates verification, identifying unsupported assumptions and evidence gaps. (d) It revises its search strategy to verify film credits and marital relationships. Red, amber, and green indicate stalled exploration, self-initiated verification, and revised exploration, respectively.
Figure 9: Local deployment of Sage-A1.5. Quantized variants of Sage-A1.5 (MoE with 35B total and 3B active parameters) run on heterogeneous hardware, are served by local runtimes through a local inference API, and carry out multi-turn scientific and engineering tasks with local agent tools. All components stay within the local environment (dashed boundary), enabling a fully on-premise agentic workflow.
Figure 10: Illustrative preview of a DeepResearch report generated Sage-A1.5
Figure 11: Long-horizon scientific reasoning and self-correction of Sage-A1.5 on a quantum optics task from CritPt (#19). Through hypothesis formulation, tool-assisted verification, conflict detection, error localization and correction, Sage-A1.5 identifies and fixes an error in its numerical verification code, resolves discrepancies between its analytical derivation and numerical calculations, and independently re-validates the results.
Figure 12: Real-world and professional workflows. Representative artifacts from ten engineering, scientific, planning, data and security workflows. Panels show implementation and simulation results, coverage plans, audit findings, data reconciliation and document processing, with key outcomes highlighted.
Figure 13: Computational analyses across three scientific domains. (a) Hydrogen delivery costs across 30 simulated sites under 2025 assumptions. The dashed horizontal line marks the assumed European cost of EUR 5.50/kg. (b) Synthetic waveform differences across spherical harmonic modes ( n=1,500n=1{,}500 per mode). Boxes show interquartile ranges, center lines indicate medians, and whiskers span the 5th–95th percentiles. (c) O/OH adsorption scaling across six metal surfaces using approximate reference values and analytical estimates. Lines show linear fits.
Figure 14: Reanalysis of shared decoding structure across mouse brain regions. (a) Reanalysis by Sage-A1.5. (b) Corresponding results reported in SeekBrain [ 41 ] (Fig. 4c,f). Left: PC1 explains 63.2% of the variance across five standardized decoding metrics in 201 brain regions, assessed against 5,000 column-wise permutations (empirical p≈2.0×10−4p\approx 2.0\times 10^{-4} ; null mean in (a), 24.0%). Right: regional PC1 scores displayed symmetrically on a bilateral Swanson flatmap. Darker blue in (a) and darker purple in (b) indicate higher PC1 scores; regions without a value are gray.
Figure 15: Substituent effects and binding modes between N-methylacetamide (NMA) and pyridine derivatives in the Sage-A1.5 investigation. (a) Sage-A1.5 implemented and executed a scientist-guided computational workflow, managing independent jobs concurrently and diagnosing and restarting failed calculations. (b) Counterpoise-corrected gas-phase energy differences relative to NMA–pyridine; negative values indicate stronger binding. Each bar shows the lowest-energy sampled pose. The 2-methyl derivative binds more strongly than initially predicted. (c) Optimized NMA–3-hydroxypyridine complexes showing ring-nitrogen binding (N-HB, upper) and the more favorable hydroxyl binding (O-HB, lower). Dashed lines indicate hydrogen bonds. Atom colors: C (black), N (blue), O (red), H (white); carbon-bound hydrogens are omitted.
Figure 16: Feedback-guided refinement of a Sc2Au6\mathrm{Sc_{2}Au_{6}} structure. (a) Accepted RwpR_{\mathrm{wp}} over eight trials. Blue circles indicate the initial state and accepted updates, while orange crosses mark rejected trials (3 and 5). The inset highlights late coordinate refinements. (b) Observed, initial, and final calculated diffraction profiles, with residuals shown below. Profiles are display-sampled CPU float64 redraws; RwpR_{\mathrm{wp}} values are from the original NPU run using all 7,500 observations.
Figure 17: Mechanistic reasoning during a historical electrochemistry replay. (a) Isolated yields of 20 historical conditions across five batches. The blue staircase tracks the best yield, reaching 89% at EXP-038 in batch 4. Annotations mark feedback-driven graph updates. (b) Evolution of mechanistic hypotheses. Solid arrows show existing connections, while dashed arrows indicate the reaction-time penalty and residence-time–quenching interaction introduced in batches 3 and 5, respectively. TS denotes transition state. These connections represent model hypotheses, not established causal relationships.
Figure 18: Iterative optimization of fluorescence spot detection. (a) Performance across eight evaluation submissions, measured by aggregate_improvement (higher is better). Annotations highlight key implementation changes. (b) Predicted and reference spots overlaid on the same DNA-FISH image with identical contrast. Green rings mark matched detections, orange crosses mark unmatched predictions, and purple plus signs mark missed reference spots.
More in this topic

Long-Horizon LLM Agents

Long-horizon large language model agents plan, use tools, and preserve task state across extended, multi-step interactions.

See all 448 papers

Explore similar work

CardsList
Oct 8, 2026

SAIL: Scientific Agentic Intelligence via a Science-Aware Loop

We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows. SAIL is developed through a science-aware improvement loop: agents built on frontier AI models analyze its task failures and construct training tasks that address the underlying capability gaps. The diagnosis examines search and evidence selection in literature tasks, scientific assumptions and reasoning in coding, and planning and revision in longer investigations. The agents draw on paper collections and scientific code repositories to build problems, interaction trajectories, and executable tasks with the required environments and tools. We repeat this loop over multiple development cycles and train SAIL through supervised fine-tuning, specialist training, multi-teacher on-policy distillation, and agentic reinforcement learning. SAIL achieves competitive performance across scientific research tasks with substantially fewer parameters than leading open-weight models.

SAIL Model Team, Boyuan Sun, Bryan Dai +9

IQuest Research

Autonomous Research AgentsAI Agents for Scientific DiscoveryLLM Agent TrainingScientific Reasoning in Language Models
AskPDF
Aug 24, 2026

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this working capability: sustained, verifiable progress toward a real-world objective. Apodex 1.1 develops this capability along two complementary dimensions. Environment Scaling expands the diversity and verifiability of executable file, search, and code environments, while Agentic Coordination Scaling trains agents to decompose long-horizon tasks, delegate parallel work, integrate asynchronous results, and replan. A shared execution harness and AgentOS maintain task state and provenance across tools and agents, and training turns environment trajectories and coordination traces into reliable behavior. Across complex professional work, finance, scientific research, mathematics, coding, and search, Apodex 1.1 reaches the leading performance band despite using a substantially smaller model than many frontier systems. The 35B-parameter Apodex 1.1 Mini further retains strong working capability in a locally deployable form. These results ground agentic intelligence in useful, verifiable work completed over time and advance our goal of building a Heavy-Duty Solver for ambitious, long-running tasks.

B. An, B. Li, B. Wang +72

Long-Horizon LLM AgentsLong-Horizon Agent TasksLLM Agent TrainingLLM Agent HarnessesMulti-Agent Collaboration
AskPDF
Aug 3, 2026

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within a growing context, making the state difficult to track and allowing incorrect self-assessments to propagate into later decisions. We reformulate long-horizon execution as a task-state management problem and propose LongHorizon-Harness, which maintains the task state explicitly outside execution and updates it only with facts independently verified from the environment. Its Manage-Execute-Audit(MEA) loop uses a manager to maintain the task state and determine the next subtask, a fresh-context executor to perform it, and a read-only auditor to verify the resulting environment state before the next round. A lightweight AgentAdapter supports interchangeable model and harness backends without modifying their native agent loops. LongHorizon-Harness improves Qwen3.7-Plus from 51.8% to 80.7% on WeaveBench, from 69.7% to 77.2% on Terminal-Bench2.1, and from 2.8% to 8.3% on OSWorld2.0. It also raises Claude Opus4.7 from 20.0% to 34.3% on an OSWorld2.0 subset, demonstrating consistent gains across models, harnesses, and interaction domains.

Ziyu Ma, Hailang Huang, Shun Zou +5

DreamX Team, Alibaba Group

Long-Horizon Agent EvaluationLong-Horizon LLM AgentsLLM Agent Harnesses
AskPDF