Overview

Agentic reasoning examines how AI systems carry out goals through sequences of decisions, tool use, and interaction with an environment, rather than producing a single answer. Common approaches include ReAct-style reasoning and acting, task decomposition, retrieval and memory, multi-agent coordination, reinforcement learning, and verification with external tools or formal solvers. Work evaluates these methods on coding, multi-hop question answering, web research, and interactive environments, increasingly measuring process quality and resource use as well as final accuracy. A central tension is that planning, more tool use, and longer reasoning can improve difficult tasks but also add cost and failure points, so agents must learn when to gather evidence, verify, or stop.

Latest papers

108 papers10 papers in the last four weeks, down 23% on the four weeks before. 0.1% of all new papers.

Jun 12, 2026

PrologMCP: A Standardized Prolog Tool Interface for LLM Agents

Frontier reasoning-tuned language models still fail on deductive tasks at depth, and the cost of improved performance through extended internal reasoning scales poorly. Symbolic delegation offers a complementary route: a language model translates the problem, while a solver performs the inference. However, current autoformalization pipelines for logic programming are typically bespoke integrations tied to particular tasks or agents. We introduce PrologMCP, a task-agnostic, open-source server that exposes Prolog as a stateful tool through the Model Context Protocol (MCP). Its compact tool interface, structured error reporting, and per-session isolation make the translate-run-inspect-repair loop a reusable primitive for MCP-capable agents. We evaluate a formalizer agent enhanced with PrologMCP against standard and reasoning LLMs (Claude Sonnet 4.6, GPT-4.1, and o4-mini) on two subsets of PARARULE-Plus: a general-purpose sample and a more challenging one targeting a specific failure mode of natural-language reasoning. On the general sample, the formalizer matches or exceeds reasoning LLMs (accuracy 1.00 vs.\ 1.00 / 0.998), with the largest gains over standard models (0.762 for GPT-4.1). On the challenging subset, the formalizer remains near-perfect (1.00 / 0.99) while reasoning LLMs drop to 0.95 / 0.94. These results suggest that delegating inference to Prolog via MCP is a robust and inspectable alternative to extended natural-language reasoning.
Jun 12, 2026

Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime

Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passages, repeated no-progress behavior, or mission-level ambiguity. On physical UAVs, however, remote reasoning is most useful when it is invoked selectively, since each call introduces latency, resource cost, backend uncertainty, and a need to validate the returned decision. This paper presents Persistent Mission Runtime (PMR), a UAV recovery framework that keeps the mission loop and safety-critical execution local while using an external agentic reasoner only as an on-demand recovery module. The reasoner selects from predefined recovery skills, and each returned decision is parsed, verified, safety-filtered, and mapped to local executor actions before it can affect flight. 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 enough to justify its operational cost. Across a fixed 400-run Gazebo/PX4 benchmark with eight scenarios, learned-CVI raises hard/ambiguous-regime success from 5.0% under local-only autonomy to 95.0%, outperforms one-shot and periodic reasoning baselines by 20.0 and 32.5 percentage points, and reduces remote-agent calls by 16.7% and logged tokens by 29.2% relative to a manually tuned rule-based invocation baseline.
Jun 3, 2026

DAR: Deontic Reasoning with Agentic Harnesses

Deontic reasoning is the task of answering questions by applying explicit rules and policies to case-specific facts, for example computing tax liability under a statute or determining the outcome of an immigration appeal. A key technical challenge for LLM-based deontic reasoning is that the relevant ruleset can be long and cross-referenced, so models may still fail to locate the rules needed for a particular reasoning step. We introduce Deontic Agentic Reasoning (DAR), an agentic reasoning setup in which the model interacts with the statutes on demand. We evaluate DAR under multiple harnesses on hard subsets of DeonticBench. Across these settings, we find that agentic harnesses can push the frontier on deontic reasoning tasks, but improvements are not uniform: weaker models often degrade on numerical tasks while consuming far more tokens.
Jun 3, 2026

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

Mobile agents are increasingly expected to operate everyday applications from screenshots and language goals, where reliable control requires reasoning over screen affordances, multi-step navigation, and future state changes. However, many agents externalize this computation as long textual chains of thought, which slows interaction, increases supervision cost, and complicates deployment. We introduce MIRAGE, a framework that learns continuous latent reasoning representations from visible textual reasoning traces. MIRAGE transfers explicit reasoning into compact hidden states, enabling the agent to reason internally without decoding long rationales. It also incorporates a generative world-model objective: latent reasoning vectors are aligned with future screenshots, encouraging the agent to anticipate upcoming interface states before acting. This turns hidden computation into both a compressed thought representation and a forward-looking model of environment dynamics. At inference time, MIRAGE reasons in continuous latent space, reducing token generation while improving execution efficiency. On AndroidWorld, MIRAGE matches explicit chain-of-thought supervised fine-tuning in the 4B ablation with a 3-5x lower decoded-token budget and improves a comparable instruction-tuned baseline by 10.2 points; on AndroidControl, it improves action grounding while generating over 75% fewer tokens.
Jun 2, 2026

TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning

Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently, large language models (LLMs) have emerged as a promising paradigm for TS quality assessment via pairwise comparison and per-dimension evaluation. However, existing approaches rely on manually predefined quality dimensions and purely text-based reasoning, leaving it unknown whether LLMs can identify truly relevant quality dimensions or perform grounded and quantitative quality comparisons. To investigate this, we construct TSQBench, a dedicated benchmark for evaluating LLMs on two progressive capabilities: (i) understanding and identifying relevant quality dimensions, and (ii) performing quality comparison under specific dimensions. Our analysis reveals that current LLMs consistently struggle with both dimension identification and evidence-grounded quality comparison. To address these limitations, we propose TSQAgent, a novel agentic reasoning framework for TS quality rating consisting of three collaborative roles: Perceiver for focused dimension selection, Inspector for dimension-wise quantitative analysis, and Adjudicator that aggregates and refines the final judgment. In particular, we introduce an agentic reasoning strategy that instills the ability to identify and prioritize the most relevant quality dimensions, and further propose an agent workflow equipped with external analytical tools to enable precise quantitative comparisons over selected dimensions. Experiments on both the proposed benchmark and eleven real-world datasets demonstrate that our framework not only substantially improves LLMs' capabilities in quality understanding and quantitative comparison but also effectively translates these improvements into better quality-aware data selection, leading to enhanced downstream performance and data efficiency.
Jun 2, 2026

Learning Reusable Agent Subroutines from Experience

Existing methods induce various forms of knowledge from agent traces, from sample workflows to programmatic skills. We propose ARISE (Agent Routine Induction from Successful Experience), which identifies recurring procedures in agent traces and synthesizes them into a reusable library of agent subroutines. Across five tasks in narrative deduction, rule application, and constraint planning, it is shown to be a more effective learning strategy than prompting methods and prose and code artifact induction methods. ARISE outperforms chain-of-thought in all ten model-task settings of the main evaluation. Compared to state-of-the-art methods in agent experience induction, our method scores 6.1 percentage points over the strongest evaluated baselines, and 11.5 percentage points over code-skill induction. In our controlled experiment, ARISE also improves average accuracy by up to 15.6 percentage points compared to formatting the induced knowledge as skills and by up to 19.1 points over rewriting it as code tools.
Jun 1, 2026

Adaptive Latent Agentic Reasoning

Large reasoning models improve performance by generating extended chain-of-thought (CoT) reasoning, but this behavior becomes inefficient when applied to LLM agents. Current LLM agents often generate verbose textual reasoning at every decision step and allocate reasoning effort nearly uniformly across turns, leading to substantial inefficiency in multi-turn agentic trajectories. We propose Adaptive Latent Agentic Reasoning (ALAR), a dual-mode framework that uses compact latent reasoning for routine turns and selectively escalates to explicit chain-of-thought when deeper deliberation is needed. ALAR learns latent reasoning by using the agent's actions as supervision anchors and is further optimized to use latent reasoning when it is sufficient for task success and reserve explicit CoT for harder decisions. Experiments on agentic search and tool-use benchmarks show that ALAR maintains comparable or better task accuracy while substantially reducing generated tokens by up to 43.6% in search and 84.6% in tool use. These results demonstrate that ALAR improves the accuracy-efficiency trade-off of LLM agents by reducing unnecessary textual reasoning while preserving explicit deliberation for harder decision steps.
May 30, 2026

Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents

Do LLM agents act on the reasoning they state? This question of process fidelity is central to LLM-based social simulation, yet hard to measure where no reference for correct behavior exists. We study it in a controlled setting: a Texas Poker simulator with a verifiable reference action for every decision by splitting the faithfulness gap into two steps: reasoning-to-conclusion (does the stated decision follow from the agent's own reasoning?) and conclusion-to-action (does the agent execute what it states?). The two steps behave very differently. Conclusion-to-action is reliable: inconsistency is 0.7% for Claude Haiku 4.5 and 1.4% for DeepSeek-Reasoner once the conclusion is read from an explicit tag, whereas free-text conclusion extraction reports 22-26%. Reasoning-to-conclusion is where fidelity frays, but not through a single dominant failure. In a step-level diagnostic the agent's errors split roughly evenly between bad inputs, borderline cases, and rule misapplication deriving a conclusion that contradicts the agent's own restated rule from inputs it estimated correctly. This composition is model-dependent: rule misapplication accounts for a third of Haiku's interpretable errors but only 8% of DeepSeek's. The one robust signal is directional: when an agent does misapply its own stated rule, it almost always (99.5% for Haiku) errs in the risk-averse direction. The override is partly hedging behavior, not a capability limit: instructing the agent to apply the rule mechanically halves the misapplication rate (13.9% to 6.8% of decisions) and raises adherence by eight points. Process-fidelity evaluation should therefore elicit machine-checkable conclusions and probe for directional biases rather than assume a single upstream failure mode, lest it conflate measurement noise with model behavior.
May 29, 2026

MAVEN: Improving Generalization in Agentic Tool Calling

Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on individual benchmarks, their ability to compose reasoning strategies, preserve intermediate states, and coordinate tools across domains remains underexplored. We present MAVEN (Modular Agentic Verification and Execution Network), a lightweight symbolic reasoning scaffold for structured decomposition, adaptive tool orchestration, and intermediate verification. We evaluate MAVEN across established tool-calling benchmarks, including BFCL v3, TauBench, Tau2Bench, AceBench, and introduce MAVEN-Bench, a stress-test benchmark for multi-step mathematical and physical reasoning with explicit verification and adversarial task composition. MAVEN-Bench exposes a substantial gap between partial reasoning quality and end-to-end task success; in direct MAVEN-Bench runs, MAVEN improves its GPT-OSS-120b base model from 48% to 71% accuracy without additional training. It also remains competitive with frontier proprietary baselines while using an open-weight backbone with an estimated cost ratio of roughly 1/10, suggesting that lightweight verification-centered scaffolds can strengthen compositional reasoning and motivate more process-aware evaluation of agents in the wild.
May 27, 2026

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a structural asymmetry: thinking (the self-contained default) and tool use (a high-variance auxiliary acting). We refer to this asymmetry as the Thinking-Acting Gap. Under standard RL recipes like GRPO, the gap manifests as two diagnostic symptoms during training: tool use is attempted on only ~30% of rollouts, and when attempted, the tool-using rollouts within a group are all-wrong on ~40% of questions, suppressing the learning signal at the tool calls that needed it. We propose AXPO (Agent eXplorative Policy Optimization): for each all-wrong tool-using subgroup, AXPO fixes the thinking prefix and resamples the tool call and its continuation, paired with uncertainty-based prefix selection. Across nine multimodal benchmarks and three scales of Qwen3-VL-Thinking, SFT+AXPO outperforms SFT+GRPO at average (+1.8pp Pass@1 and +1.8pp Pass@4 at 8B on average) and 8B with SFT+AXPO surpasses the 32B Base on Pass@4 with 4 times fewer parameters.
May 27, 2026

Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning

Role-based LLM multi-agent systems need adaptive role pools, yet adapting such systems is not merely a matter of prompt optimization: roles often carry structural obligations, including capability coverage, message compatibility, validation, final-answer aggregation, and parser-compatible output protocols. Existing systems either fix the role inventory and lose adaptivity, or allow unconstrained generation to induce role drift, removing structurally necessary roles and breaking answer contracts. We formulate this as contract-preserving role evolution, requiring every committed edit to preserve five structural contracts (capability, communication, validation, aggregation, output protocol). We instantiate this formulation in SERO, a Self-Evolving Role Orchestration framework that evolves a typed role-card pool through credit-guided retrieval, a credit-ranked communication DAG with a protected terminal aggregator and conditional validator repair, and a contextual-bandit controller whose LLM-proposed edits are committed only when they preserve the contracts and improve task score. Experiments on real-world reasoning benchmarks across three LLM backbones confirm the value of contract-preserving role evolution.
May 27, 2026

Plan Before Search: Search Agents Need Plan

Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, this paradigm overlooks two fundamental factors: the dependency structure among sub-skills, and the possibility that distillation is not the only route to capability acquisition. We study this through Plan, a structured agentic behavior for multi-hop retrieval that decomposes a question into ordered sub-questions before any retrieval is performed, so that each search step can be anchored to a pre-designed sub-question instead of drifting under the influence of partially relevant documents retrieved earlier. However, across three model families spanning 3B to 14B parameters, we find that an identical reward signal induces qualitatively different RL failure modes. This phenomenon indicates that successful training hinges not only on reward design but also on model-specific feasibility conditions: sufficient initial entropy, training stability, and prerequisite sub-skills. Motivated by this, we propose a self-bootstrapping paradigm in which a small-scale seed model generates filtered trajectories that activate Plan in any target model, eliminating the need for distillation from an external stronger model. Our pipeline activates Plan across every tested model and consistently outperforms competitive baselines on multi-hop QA benchmarks.
May 25, 2026

Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3

We systematically investigate all 25 public ARC-AGI-3 games and find that every one is reachable through non-intelligent strategies: 10 in a single blind step, 5 after one probing action, 1 via repeated ACTION1 presses, 1 via diverse exploration, and 8 via single repeated actions with sufficient budget (50-200 steps). A library-level null-coordinate vulnerability additionally bypasses 18 games in 1 step. This benchmark critique implies the public evaluation set cannot discriminate intelligent exploration from trivial heuristics - the private 55-game evaluation is the only genuine intelligence test. Against this backdrop, we present AERA (Adaptive Epistemic Reasoning Agent), a three-phase (EXPLORE / VERIFY / PLAN) agent achieving RHAE=0.2116 (4/25 solved) on these 25 games with Qwen2.5-0.5B, while random and no-explore baselines score 0.0000. We formalise AERA through a Speed--Depth trade-off framework: under a convexity assumption (proved for a class of environments in the Appendix), RHAE's quadratic form emerges as a second-order penalty for deviating from the Pareto frontier between action efficiency and information gain. Contributions: (i) a benchmark validity analysis showing that current interactive reasoning benchmarks fail to measure the exploration they claim to require, and (ii) the EXPLORE-before-PLAN framework and model-capability x exploration interaction. The linked code track entry achieves RHAE=0.30 on the full 55-game private evaluation. Code: CC0.
May 25, 2026

Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents

Visual agents employ external visual tools within visual chains of thought to incorporate fine-grained evidence. While prior work has mainly studied these tools in visual search tasks, their role in more complex visual reasoning remains underexplored. In this paper, we move beyond simple visual search tasks to investigate more challenging tasks, including 3D spatial reasoning and medical visual question answering, where agents must integrate tool-acquired local evidence with the global context. We identify a {tool-use collapse phenomenon: models progressively stop using tools while still achieving higher task accuracy. Moreover, we observe a clear asymmetry: (i) completely eliminating tool use degrades performance, whereas (ii) incentivizing tool use yields only marginal gains despite substantially increasing usage. We find that vanilla training and tool-use encouragement both reduce rollout diversity, explaining why higher tool use does not yield stronger reasoning performance. Motivated by these findings, we add an entropy regularization term to encourage diverse rollout exploration, achieving the best performance despite gradually declining tool usage. Overall, our findings suggest a training-time view of tools as scaffolding, where broader exploration over language generation and visual tool invocation improves reasoning despite tool-use collapse. Project page: https://scaffolded-exploration.github.io
May 24, 2026

DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces, incorrect intermediate reasoning may be adopted and amplified, leading to confident but wrong consensus; multi-round communication also increases token consumption, latency, and inference cost. In this paper, we propose a controlled-communication coordination framework named DarkForest. DarkForest first keeps agents independent, so each agent produces an answer without seeing the others' outputs. It then parses the raw responses into structured candidate records, groups semantically equivalent candidates into clusters, and estimates a calibrated belief distribution over these clusters using agent reliability, confidence, parse quality, support-pattern reliability, and independence corrections. A coordinator receives only policy-permitted evidence from this belief state with controlled communication. Experiments on six reasoning benchmarks show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7% on benchmark metrics, and reduces token consumption by up to 6.5×6.5\times compared with communication-heavy baselines.
May 22, 2026

Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents

ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow, redundant, or poorly targeted trajectories. Prior work has explored rubrics as external quality signals, but existing uses are mostly evaluative rather than action-guiding: rubrics typically serve as training-time rewards or post-hoc evaluators of completed outputs, and in deep-research settings they are often coarse-grained and report-level rather than step-level. We introduce Co-ReAct, a rubric-guided action-selection framework that uses rubrics as step-level guidance during inference. At each decision step, Co-ReAct injects a rubric into the agent's context to guide the next Reason-or-Act decision, specifying what the agent should target in evidence seeking, search, reasoning, or self-evaluation. To make this guidance reliable, we train a dedicated rubric generator with GRPO. Unlike prior pairwise or binary preference formulations, our objective optimizes a list-wise Spearman rank-correlation reward against multi-judge expert consensus rankings, encouraging rubrics that are discriminative rather than merely plausible. On DeepResearchBench and SQA-CS-V2, Co-ReAct consistently improves over ReAct and representative test-time compute baselines across search agents built on both 8B/14B open-source and frontier closed-source base models. The trained rubric generator can also serve as a drop-in component that improves these baselines without changing their underlying decision mechanisms. Our code is publicly available at https://github.com/ZBWpro/Co-ReAct.
May 21, 2026

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the presence, structure, or horizon of planning, these systems dramatically increase reasoning length, yielding inefficient token use without reliable accuracy gains. We argue efficient agentic reasoning benefits from decomposing decision-making into three systems: simulative reasoning (System II) grounding deliberation in future-state prediction via a world model; self-regulation (System III) deciding when and how deeply to plan via a learned configurator; and reactive execution (System I) handling fine-grained action. Simulative reasoning provides unified planning across diverse tasks without per-domain engineering, while self-regulation ensures the planner is invoked only when needed. To test this, we develop SR2^2AM (Self-Regulated Simulative Reasoning Agentic LLM), realizing both as distinct stages within an LLM's chain-of-thought, with the LLM as world model. We explore two instantiations: recording decisions from a prompted multi-module system (v0.1) and reconstructing structured plans from traces of pretrained reasoning LLMs (v1.0), trained via supervised then reinforcement learning (RL). Across math, science, tabular analysis, and web information seeking, v0.1-8B and v1.0-30B achieve Pass@1 competitive with 120-355B and 685B-1T parameter systems respectively, while v1.0-30B uses 25.8-95.3% fewer reasoning tokens than comparable agentic LLMs. RL increases average planning horizon by 22.8% while planning frequency grows only 2.0%, showing it learns to plan further ahead rather than more often. More broadly, learned self-regulation instantiates a principle we expect to extend beyond planning to how agents govern their own learning and adaptation.
May 19, 2026

CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning

Chain-of-thought (CoT) is a standard approach for eliciting reasoning capabilities from large language models (LLMs). However, the common CoT paradigm treats thinking as a prerequisite for answering, which can delay access to plausible answers and incur unnecessary token costs even when the model is able to identify an answer before extended thinking, a behavior known as performative reasoning. In this paper, we introduce CopT, a reformulated reasoning pipeline that reverses the usual order of thinking and answering. Instead of thinking before answering, CopT first elicits a draft answer and then invokes subsequent on-policy thinking conditioned on its own draft answer for reflection and correction. To assess whether the draft answer should be trusted, CopT recasts continuous embeddings as inference-time contrastive verifiers. Specifically, it contrasts the model's support for the same generated tokens under discrete-token inputs and continuous-embedding inputs, yielding a sequence-level reverse KL estimator for answer reliability. Our analysis shows that under certain assumptions, the expected estimate equals the mutual information between the unresolved latent state and the emitted answer token, explaining why it captures answer-relevant uncertainty rather than arbitrary uncertainty in the latent state. When the answer is deemed insufficiently reliable, CopT performs further on-policy thinking, where a second KL estimator dynamically controls draft-answer visibility, preserving useful partial information while reducing the risk of being misled by unreliable content. Across mathematics, coding, and agentic reasoning tasks, CopT improves peak accuracy by up to 23% and reduces token usage by up to 57% at comparable or higher accuracy, without any additional training. The code is available at https://github.com/sdc17/CopT.
May 17, 2026

Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps

Frontier deep research agents (DRAs) are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks measure factual recall, single-hop QA, or generic agentic skill, and miss the multi-document, decision-grade deliverables DRAs are asked to produce. We introduce a benchmark of 70 SME-authored management consulting prompts, each embedding cognitive traps that penalize surface-pattern reasoning. Three frontier agents, namely Claude Opus4.6, OpenAI o3-deep-research and Gemini3.1Pro deep-research, are scored on two complementary layers: deterministic binary verifiers (mean 14.9 per task) and a five-criterion 0--3 SME rubric (Data Integrity, Analytical Rigor, Relevance & Focus, Execution Precision, Format & Deliverability), combined into a Verifier-Rubric Score (VRS, 0--100). Acceptance under a joint threshold (rubric mean ≥2.5\geq 2.5 and verifier pass rate ≥80%\geq 80\%) is uniformly low: o3 15.7%, Claude 12.9%, Gemini 12.9%. Pairwise differences are statistically indistinguishable. On the continuous VRS, o3 leads (61.4[CI: 55.2,,67.5]), followed by Gemini (52.6) and Claude (38.5); the o3--Claude gap (Δ=22.9Δ{=}22.9, p<0.001p{<}0.001) survives Bonferroni correction. No agent averages above the rubric's ``adequate'' threshold of 2.0; no agent's mean verifier pass rate reaches the 80% acceptance floor. Each agent fails distinctively: Claude leads on data fabrication and file-access failures; o3 propagates cascading computation errors; Gemini oscillates between the highest perfect-verifier rate and the most catastrophic collapses. The benchmark, evaluation code, and full prompt corpus are publicly released.
May 15, 2026

Argus: Evidence Assembly for Scalable Deep Research Agents

Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of the art systems scale inference time compute via parallel search and aggregation. Yet deep research answers are composed of complementary pieces of evidence, which parallel rollouts often duplicate rather than complete, yielding diminishing returns while pushing the aggregation context toward the model's limit. We propose Argus, an agentic system in which a Searcher and a Navigator cooperate to treat deep research as assembling a jigsaw from complementary evidence pieces, rather than brute forcing the whole answer in parallel. The Searcher collects evidence traces for a given sub-query through ReAct-style interaction. The Navigator maintains a shared evidence graph, verifying which pieces are still missing, dispatching Searchers to gather them, and reasoning over the completed graph to produce a source-traced final answer. We train the Navigator with reinforcement learning to verify, dispatch, and synthesize, while independently training the Searcher to remain a standard ReAct agent. The resulting Navigator supports rollouts with a single Searcher or many in parallel without retraining. 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. With 64 Searchers it reaches 86.2 on BrowseComp, surpassing every proprietary agent we benchmark, while the Navigator's reasoning context stays under 21.5K tokens.
May 12, 2026

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition

Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reasoning decisions in advance. These scaffolds are effective when their prescribed structure matches the task, but brittle when solving the task requires adapting the structure of reasoning itself. We introduce Deep Reasoning -- an inference-time approach for constructing task-specific scaffolds through structured meta-reasoning. Deep Reasoning uses a formal language that represents meta-reasoning as executable decompositions over associative inference, formal computation, and recursive subproblem solving, enabling decomposition principles to be encoded as in-context examples that guide test-time scaffold construction. We instantiate this approach in a general-purpose agent (DOLORES) that distributes complex tasks across more controlled reasoning threads. We evaluate it against state-of-the-art scaffolding methods across four hard benchmarks: multi-hop reasoning, long-chain question answering, long-context aggregation, and deep research-style information seeking. DOLORES outperforms all evaluated scaffolds across three model sizes and two model families, improving over the strongest evaluated scaffold baseline by 24.8% on average. DOLORES distributes cognition across structured, lower-load reasoning threads, thereby reducing premature termination and hallucinations. This advantage can even bridge the scaling gap, with an 8B version surpassing all evaluated 32B baselines from the same family in more than half the settings. These results point toward future agentic systems that treat scaffolding as adaptive reasoning, constructing the structure each task requires just-in-time.
May 11, 2026

M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models

While reasoning has become a central capability of large language models (LLMs), the reasoning patterns required for different scenarios are often misaligned. Mathematical reasoning typically relies on intrinsic logic to solve closed-world problems in a single response, whereas agentic reasoning requires not only internal reasoning but also multi-turn interaction with external environments, interleaving thought and action. This misalignment prevents mathematical and agentic reasoning from effectively benefiting from each other, often yielding unstable reasoning behavior and only limited performance gains under multi-task learning. In this paper, we propose M2A, a novel paradigm that synergizes mathematical and agentic reasoning via model merging. To avoid overfitting to superficial reasoning patterns under joint training, M2A operates directly in parameter space: it identifies the feature subspace critical for agent behavior, and merges the mathematical reasoning task vector only along its null space, thereby injecting reasoning capability along directions that do not perturb agent behavior. Unlike SFT or RL, M2A requires no additional gradient-update and exposes the merging coefficient as a simple knob for controlling reasoning length. Experiments in a challenging real-world coding agent setting show that our method effectively extends agentic reasoning depth and delivers substantial performance improvements. Applied to a fine-tuned Qwen3-8B, M2A improves its SWE-Bench Verified resolved rate from 44.0% to 51.2% without retraining the model. Code is available at https://github.com/laplucky/M2A.git.
May 10, 2026

Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

In this paper, we propose the first VLM‾\underline{\textbf{M}} a‾\underline{\textbf{a}}gentic r‾\underline{\textbf{r}}easoning framework for few-s‾\underline{\textbf{s}}hot multimodal T‾\underline{\textbf{T}}ime S‾\underline{\textbf{S}}eries C‾\underline{\textbf{C}}lassification (MarsTSC\textbf{MarsTSC}), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmarks demonstrate that MarsTSC\textbf{MarsTSC} delivers substantial and consistent performance gains across 6 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence.
May 8, 2026

When Independent Sampling Outperforms Agentic Reasoning

We study how to allocate inference-time compute for competitive programming under fixed budgets. Evaluating 216 Codeforces problems across Divisions 1-3, we compare agent-based reasoning with repeated independent sampling (k-shot) as a function of both cost and number of model calls. Across models and difficulty levels, k-shot consistently achieves a better accuracy-cost and accuracy-query tradeoff. This gap persists despite prompt caching in agent frameworks, indicating lower per-call effectiveness. Our results show that, for self-contained algorithmic tasks, independent exploration can outperform deeper agentic reasoning under realistic resource constraints. We also provide a budget-allocation analysis when the inference budget is fixed, and prove that a cost-optimal solver minimizes the principled metric log failure likelihood per dollar.
May 7, 2026

AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases

We present AgenticRAG, a practical agentic harness for retrieval and analysis over enterprise knowledge bases. Standard RAG pipelines place significant burden of grounding on the search stack, constraining the language model to a fixed candidate set chosen deep in the retrieval process. Our approach reduces this overdependence by layering a lightweight harness on top of existing enterprise search infrastructure, equipping a reasoning LLM with search, find, open, and summarize tools enabling the model to iteratively retrieve information, navigate within documents, and analyze evidence autonomously. On three open benchmarks we observe substantial gains: 49.6%49.6\% recall@1 on BRIGHT (+21.8 pp over the best embedding baseline), 0.96 factuality on WixQA (+13%+13\% relative improvement), and 92%92\% answer correctness on FinanceBench--within 2 pp of oracle access to true evidence. Ablation studies show that the most significant factor is the shift from single-shot retrieval to agentic tool use (5.9×5.9\times improvement), while multi-query search and in-document navigation contribute to both quality and efficiency. We present various design choices in our agentic harness that were informed by pre-production deployments. Our results demonstrate its suitability for real-world enterprise production environments.
May 6, 2026

BALAR : A Bayesian Agentic Loop for Active Reasoning

Large language models increasingly operate in interactive settings where solving a task requires multiple rounds of information exchange with a user. However, most current systems treat dialogue reactively and lack a principled mechanism to reason about what information is missing. We propose BALAR (Bayesian Agentic Loop for Active Reasoning), a task-agnostic outer-loop algorithm that requires no fine-tuning and enables multi-turn interaction between an LLM agent and a user. BALAR maintains a structured belief over latent states, selects clarifying questions by maximizing expected mutual information, and dynamically expands its state representation when the current one proves insufficient. We evaluate BALAR on three diverse benchmarks: AR-Bench-DC (detective cases), AR-Bench-SP (thinking puzzles), and iCraft-MD (clinical diagnosis). BALAR outperforms all baselines across the three benchmarks, with 14.6% higher accuracy on AR-Bench-DC, 38.5% on AR-Bench-SP, and 30.5% on iCraft-MD. We further study whether BALAR can serve as a teacher for a questioning policy through supervised fine-tuning (SFT), direct preference optimization (DPO), and dense-reward reinforcement learning (RL). Across 18 iCraft-MD replications, distilling BALAR into a Llama-8B yields relative gains in frozen-Qwen final-answer accuracy of 8.1% with SFT, 10.9% with DPO, and 12.1% with RL over the untuned policy.
May 4, 2026

FitText: Evolving Agent Tool Ecologies via Memetic Retrieval

A semantic gap separates how users describe tasks from how tools are documented. As API ecosystems scale to tens of thousands of endpoints, static retrieval from the initial query alone cannot bridge this gap: the agent's understanding of what it needs evolves during execution, but its tool set does not. We identify this retrieval interface, not planning, as the binding constraint on end-to-end agent performance, and introduce FitText, a training-free framework that makes retrieval dynamic by embedding it directly in the agent's reasoning loop. FitText treats retrieval as test-time evolution of hypotheses: the agent generates natural-language pseudo-tool descriptions (revisable beliefs about the tool it needs), refines them iteratively using retrieval feedback, and explores diverse alternatives through stochastic generation. Memetic Retrieval adds evolutionary selection pressure over candidate descriptions, guided by a tool memory that avoids redundant search. On ToolRet (three domains), FitText's reformulation strategies improve NDCG@5 by 2.7 to 10.6 points over static query retrieval across all base models; on StableToolBench (16,464 APIs) with GPT-5.4-mini, Memetic reaches an 84.3% pooled pass rate, a 26.7-point absolute gain over static query retrieval.
Apr 30, 2026

Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents

Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we demonstrate that this consensus does not always hold: in the presence of semantic distractors, tool-augmented reasoning does not necessarily outperform native CoT. To explain this performance gap, we propose a Factorized Intervention Framework that isolates the cost of prompt formatting, the overhead of the tool-calling protocol, and the actual gain from executing tools. Our analysis reveals a critical tradeoff: under semantic noise, the gains from tools often fail to offset the "tool-use tax", which is the performance degradation introduced by the tool-calling protocol itself. To address this, we introduce G-STEP, a lightweight inference-time gate to mitigate protocol-induced errors. While this yields partial recovery, our findings suggest that more substantial improvements still require strengthening the model's intrinsic reasoning and tool-interaction capabilities.
Apr 25, 2026

Discovering Agentic Safety Specifications from 1-Bit Danger Signals

Can large language model agents discover hidden safety objectives through experience alone? We introduce EPO-Safe (Experiential Prompt Optimization for Safe Agents), a framework where an LLM iteratively generates action plans, receives sparse binary danger warnings, and evolves a natural language behavioral specification through reflection. Unlike standard LLM reflection methods that rely on rich textual feedback (e.g., compiler errors or detailed environment responses), EPO-Safe demonstrates that LLMs can perform safety reasoning from a strictly impoverished signal in structured, low-dimensional environments: the agent never observes the hidden performance function R∗R^*, only a single bit per timestep indicating that an action was unsafe. We evaluate on five AI Safety Gridworlds (Leike et al., 2017) and five text-based scenario analogs where visible reward RR may diverge from R∗R^*. EPO-Safe discovers safe behavior within 1-2 rounds (5-15 episodes), producing human-readable specifications with correct explanatory hypotheses about hazards (e.g., "X cells are directionally hazardous: entering from the north is dangerous"). Critically, we show that standard reward-driven reflection actively degrades safety: agents reflecting on reward alone use the loop to justify and accelerate reward hacking, proving that reflection must be paired with a dedicated safety channel to discover hidden constraints. We further evaluate robustness to noisy oracles: even when 50% of non-dangerous steps produce spurious warnings, mean safety performance degrades by only 15% on average, though sensitivity is environment-dependent, as cross-episode reflection naturally filters inconsistent signals. Each evolved specification functions as an auditable set of grounded behavioral rules discovered autonomously through interaction, rather than authored by humans as in Constitutional AI (Bai et al., 2022).
Apr 19, 2026

ARMove: Learning to Predict Human Mobility through Agentic Reasoning

Human mobility prediction is a critical task but remains challenging due to its complexity and variability across populations and regions. Recently, large language models (LLMs) have made progress in zero-shot prediction, but existing methods suffer from limited interpretability (due to black-box reasoning), lack of iterative learning from new data, and poor transferability. In this paper, we introduce ARMove, a fully transferable framework for predicting human mobility through agentic reasoning. To address these limitations, ARMove employs standardized feature management with iterative optimization and user-specific customization: four major feature pools for foundational knowledge, user profiles for segmentation, and an automated generation mechanism integrating LLM knowledge. Robust generalization is achieved via agentic decision-making that adjusts feature weights to maximize accuracy while providing interpretable decision paths. Finally, large-small model synergy distills strategies from large LLMs (e.g., 72B) to smaller ones (e.g., 7B), reducing costs and enhancing performance ceilings. Extensive experiments on four global datasets show ARMove outperforms state-of-the-art baselines on 6 out of 12 metrics (gains of 0.78% to 10.47%), with transferability tests confirming robustness across regions, users, and scales. The other 4 items also achieved suboptimal results. Transferability tests confirm its 19 robustness across regions, user groups, and model scales, while interpretability 20 analysis highlights its transparency in decision-making. Our codes are available at: https://anonymous.4open.science/r/ARMove-F847.