Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks

• URL: http://arxiv.org/abs/2608.05144v2
• Date: Fri, 07 Aug 2026 16:35:04 GMT
• Title: Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
• Abstract summary: We present Argus, a persistent, self-evolving runtime in which Manager, Planner, Engineer, and Reviewer execute bounded missions over durable project state.<n>Argus separates stable user intent from operational objectives, constraints, and verification criteria, and admits memories, skills, procedures, verifiers, routing decisions, and rejected routes only after role-owned review and, when available, task-native verification.
• Score: 38.52523278435824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a misspecified objective. We present Argus, a persistent, self-evolving runtime in which Manager, Planner, Engineer, and Reviewer execute bounded missions over durable project state. Argus separates stable user intent from operational objectives, constraints, and verification criteria, and admits memories, skills, procedures, verifiers, routing decisions, and rejected routes only after role-owned review and, when available, task-native verification. Model weights remain fixed; self-evolution occurs through persistent runtime state and control policy, with autonomous execution between operator-owned escalation points. Across seven GPT-5.5 benchmark arenas, Argus achieves about 78% on SWE-Bench Pro versus 59% for Direct Copilot while using 1.41 times the aggregate tokens. After verification-gated self-evolution, mature SWE-Bench waves use 21% fewer solve-input tokens and 15% less active workflow time per task than startup waves, while recording 34 verifier recoveries and 22 strict review-loop rescues. Argus also reaches 76.8% on AARRI-Bench and a 28.0-point gap on mathematical data synthesis, with competitive GPU-kernel and language-model-training results. Beyond benchmarks, an optimized RWKV6 kernel was merged upstream; a multi-day mathematics campaign retained falsified routes and proof-backed frontier updates; and six paper pipelines completed 254 missions with 16 stage rollbacks. These results show that a fixed-weight, self-evolving harness can revise, recover, and accumulate verified approaches while producing structured trajectories for future supervised and reinforcement learning.

Related papers

• ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training [66.72708893922605]
  Post-training of large multimodal models should add new capabilities while preserving those from pre-training.<n>SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting.<n>We introduce ReDraft, which obtains both from the model's own failures.
  arXiv  Detail & Related papers  (2026-09-15T04:59:03Z)
• Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course [5.9756241643216255]
  Large language model (LLM)-powered agents can be accurate on average yet unreliable in production.<n>We present a self-evolving framework that reduces this gap by identifying unstable, low-consistency steps in agent trajectories.<n>On AppWorld with ReAct/GPT-4.1, our framework raises the fraction of tasks that succeed in all five runs by +16 points on same-task evaluation and +13 points on similar-task generalization.
  arXiv  Detail & Related papers  (2026-09-08T14:53:43Z)
• Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories [16.13133177152883]
  Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed.<n>We identify this post-retrieval reuse step as a distinct bottleneck for long-horizon trajectory memory.<n>We instantiate the framework with query-conditioned reuse (QCR), a deliberately simple target-bound note that records a reusable procedure.
  arXiv  Detail & Related papers  (2026-08-13T05:39:49Z)
• Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence [86.61561123749011]
  We introduce Apodex Discovery, a framework for building and evaluating discoverative AI through the heavy-duty solver.<n>First, a problem-scouting process surveyed 561 industries across 16 sectors, assembled 423 high-value real-world problems, and selected 20 for the initial release.<n>Second, a common environment-task-episode abstraction provides data, tools, constraints, feedback, trajectory recording, and verification of intermediate artifacts and final submissions.
  arXiv  Detail & Related papers  (2026-08-11T18:48:40Z)
• Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions? [3.9561795512466413]
  Current benchmarks primarily measure end-task success or single-frame grounding.<n>This is difficult because inference, remote input, app rendering, and screenshot capture are asynchronous.<n>We introduce Desktop-Delta Bench (DDB), an offline step-level benchmark with 2,013 human-verified instances from novel, multi-app Linux trajectories.
  arXiv  Detail & Related papers  (2026-07-28T17:49:51Z)
• Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime [1.189955933770711]
  On physical UAVs, remote reasoning is most useful when it is invoked selectively.<n>This paper presents Persistent Mission (PMR), a recovery framework that keeps the mission loop and safety-critical execution local.<n>PMR introduces learned Cognitive Value of Invocation (learned-CVI), a compact admission gate that estimates when remote agentic reasoning is likely to improve near-term mission progress.
  arXiv  Detail & Related papers  (2026-06-12T07:57:47Z)
• ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking [2.2573512203799626]
  We propose ReacTOD, a bounded neuro-symbolic architecture that reformulates NLU as discrete tool calls within a self-correcting ReAct loop governed by deterministic validation.<n>A bounded ReAct loop enables iterative self-correction, improving accuracy by up to 9.3 percentage points over single-pass inference on MultiWOZ.
  arXiv  Detail & Related papers  (2026-05-18T20:06:04Z)
• Argus: Evidence Assembly for Scalable Deep Research Agents [74.04848873346145]
  We propose a system in which a Searcher and a Navigator cooperate to treat deep research as assembling a jigsaw from complementary evidence pieces.<n>We train the Navigator with reinforcement learning to verify, dispatch, and synthesize, while independently training the Searcher to remain a standard ReAct agent.<n>With both Searcher and Navigator built on a 35B-A3B MoE backbone, Argus gains 5.5 points with a single Searcher and 12.7 points with 8 parallel Searchers, averaged over eight benchmarks.
  arXiv  Detail & Related papers  (2026-05-15T17:29:27Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents [59.626170560327274]
  We present textbfClawForge, a generator-backed benchmark framework for executable command-line categories under state conflict.<n>We instantiate this framework as the ClawForge-Bench (17 scenarios, 6 ability categories)
  arXiv  Detail & Related papers  (2026-05-13T21:34:08Z)
• LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification [35.08680804423239]
  Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive.<n>We propose Latent-Then-Explicit Reasoning (LaTER), a two-stage paradigm that first performs bounded exploration in a continuous latent space.<n>LaTER projects final-layer hidden states back to the input embedding space, preserves the latent KV cache, and uses entropy and model-native stop-token probes to decide when to switch.
  arXiv  Detail & Related papers  (2026-05-08T06:23:58Z)
• A Rubric-Supervised Critic from Sparse Real-World Outcomes [87.11204512676193]
  Real-world coding agents operate with humans in the loop, where success signals are typically noisy, delayed, and sparse.<n>We propose a process to learn a "critic" model from sparse and noisy interaction data, which can then be used both as a reward model for either RL-based training or inference-time scaling.
  arXiv  Detail & Related papers  (2026-03-04T07:23:54Z)
• Can We Predict Before Executing Machine Learning Agents? [74.39460101251792]
  We formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons.<n>We demonstrate that LLMs exhibit significant predictive capabilities when primed with a Verified Data Analysis Report.<n>We instantiate this framework in FOREAGENT, an agent that employs a Predict-then-Verify loop, achieving a 6x acceleration in convergence while surpassing execution-based baselines by +6%.
  arXiv  Detail & Related papers  (2026-01-09T16:44:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.