Anna Mazhar, Seiji Maekawa, Nikita Bhutani · cs.CL, cs.AI
Agents 97%
Abstract
Large language model agents must discover relevant tools from large libraries, e.g., thousands of tools, as new needs arise during task execution. When several candidates could satisfy the same need, execution may be required to identify the relevant one. Investigating candidates in a shared trajectory can leave alternatives unexplored or allow failed attempts to influence subsequent reasoning. To address this, we present BRIA (BRanch-Inspect-Adopt), a simple yet effective agent that temporarily isolates candidate investigations in separate branches. Each branch retrieves and executes tools to investigate its candidate; a task agent inspects the resulting execution evidence and adopts only useful results into its continuing trajectory. BRIA retrieves additional tools as new capability needs arise during task execution. We evaluate BRIA on PlanBench-XL and MCP-Atlas using a shared pool of 1897 tools, three language models, and static and adaptive retrieval baselines. Across all settings, BRIA matches or exceeds the strongest retrieval baseline. On MCP-Atlas, it achieves an average claim score of 89.77, compared with 75.40 for MCP-Zero, a gain of 14.37 percentage points. BRIA also lies on the Pareto frontier for task performance and input-token cost.
Large language model (LLM) agents are increasingly evaluated on long-horizon tasks, including autonomously running a business. Existing benchmarks for this setting are almost exclusively English-language, Western in retail context, and single-agent, with the agent observing the business directly. We study how these results transfer to a multi-agent Indic setting. We introduce KiranaBench, a simulated Indian general store in which four roles (manager, cashier, helper, and bookkeeper) are each played by a separate LLM agent. Interactions with customers and suppliers occur in English, Hindi, or Hinglish, and product demand is calibrated to India's national Household Consumption Expenditure Survey. Evaluating four open-weight LLMs, we find that all fall far short of a fixed-rule shopkeeper baseline: the best model earns only one-eighth of the baseline's profit, and two models finish below an unmanaged shop. Performance is also consistently lower for Hindi and Hinglish than for English supplier communication. KiranaBench offers evidence that current LLM agents are not yet reliable for autonomously operating small businesses in India, and provides a testbed for developing agents suited to settings that are long-horizon, collaborative, and multilingual.
Yuhan Sun, Jiaxin Zhao, Yongdong Luo et al. · cs.CL
Multi-agent 96%Agents 45%
Abstract
In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answer gives only indirect feedback to the subagents. An LLM judge can score the performance of the subagents, but these scores depend on the judge's own assessment of the quality of subagents' responses. We present MultiAgent-OPD, which combines on-policy distillation with reinforcement learning to jointly train a shared-parameter Leader-Searcher-Answerer team end to end. We first train a Teacher in a Searcher-Answerer workflow using answer correctness. During team training, the frozen Teacher scores student-generated search and summary tokens to provide local process supervision for the Searchers, while the Leader learns from team success and the Answerer from candidate correctness. Across seven datasets, the trained system reaches 38.68% macro avg@4, exceeding Prompted Critic by 4.06 percentage points and C-MAS + RL, the trained cascaded multiagent system, by 2.61 percentage points. The team also solves more questions within four attempts.
Sam Partee, River Stevens, Thierry Damiba et al. · cs.LG, cs.IR
Agents 96%
Abstract
A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list: the roughly 8,200 tools on the platform we study have definitions that together exceed the context window of any model we evaluate. We present Tool Recommendation, a deployed system that gives an agent all of them, hundreds of times more than a typical MCP server exposes, through a fixed interface of three tools. It runs at the gateway between agent and tools, executing every call under the end user's own credentials and checking it against the user's consent for each service and the tools the agent may use. We evaluate it on both a public retrieval benchmark and billed end-to-end session cost. On ToolRet, Tool Recommendation places every tool a query needs in the top ten 57% more often than BM25, a lexical ranking that commercial tool search offers, and compares favorably with published systems up to nine times its size. In paired multi-step workflows, its first recommendation covered every required tool in 93% of Codex sessions, and against a fixed list of 100 tools it cut input tokens by 17% with Codex and 40% with Claude Code and the total bill in all 14 runs, by up to 40%, with no change in task completion.
The web is not static or uniform. Websites that serve the same purpose can look and navigate very differently. Even within a single site, successive redesigns can change how familiar features are presented and accessed. Humans adapt to this by recognizing familiar interaction patterns and reusing what they already know. We give web agents a similar ability with WebMix, a mixture hypernetwork that adapts them to unseen interfaces by composing previously trained low-rank adapters. WebMix begins with a bank of adapters trained on source interfaces. At deployment, a scout agent explores the target interface and summarizes its observations into a compact manual. A lightweight router uses this manual to predict mixing coefficients over the adapter bank, which combine the existing adapters into a new one for inference. Adapting to a new interface takes only a scouting run and a forward pass, without gradient updates on the target. With Qwen and Llama models, we evaluate domain transfer on TimeWarp and WebArena-Lite-v2, and version transfer on TimeWarp. In all three settings, WebMix matches or outperforms in-context learning and LoRA baselines, often matching the average success of specialists trained directly on those interfaces. On TimeWarp domain transfer, it gains about 8 percentage points on average over the best baseline with both models. These gains do not come at the cost of seen interfaces, where WebMix keeps its lead, and extend to version transfer. Adapting to a new interface can therefore rely on exploration and composition instead of retraining.
Open-ended tool agents can complete the same objective through different tool paths, and their quality depends jointly on the interaction trace, environment state, and final artifacts, so such tasks rarely admit an executable ground-truth reward. The central challenge is therefore to construct a reward from existing experience that exposes the current policy's failures while remaining stationary during optimization. We introduce Reward Engine, which, like a self-motivated student, first works out what success requires and then optimizes toward it. From the task and initial trajectories, it builds a RewardPack of testcases for required correctness and rubrics for graded quality, each executed as a check that returns a judgment with evidence. The frozen RewardPack then guides the agent to revise and select its outputs, and can also serve as a reward for reinforcement learning. On WorkBuddy Bench Office and Claw-Eval, the constructed reward largely agrees with the benchmark graders, not reversing their ordering on 82.3\% and 80.5\% of candidate pairs. Used to revise executions, it raises three-run consistency ($\mathrm{Pass}^{3}$) over Baseline from 45.0\% to 54.0\% and from 78.4\% to 83.7\%.
Tool-augmented language-model agents rely on interface text: tool descriptions, argument schemas, and the candidate tool list shown at inference time. These interfaces often change after deployment even when the underlying tool semantics remain fixed, creating a practical reliability problem for function-calling systems. We study this failure mode as interface drift and evaluate whether a lightweight, training-free repair layer can recover robustness without retraining the base model. Our method, SchemaShield-Lite, combines schema validation, candidate-set retry for missing tool names, and one-shot constrained repair. On Qwen3.5-9B, it raises DICE-300 accuracy from 0.717 to 0.813 and BFCL-200 accuracy from 0.580 to 0.805, recovering 19/22 and 33/45 drift-induced failures with no observed repair harms. Naive retry does not explain the gains. Ablations show that candidate-set drift, especially distractor tools, accounts for most observed damage, while description and schema edits alone are less harmful. The results position validation-and-repair as a practical robustness layer for deployed LLM-agent tool use.
Most retrieval-augmented systems treat literature search as a single retrieval step followed by summarization. Real literature research works differently: the investigator's understanding of the question changes as they read, new subquestions appear, and evidence is weighed, not just collected. We present Optimist Deep Research, an open-source agent that runs literature research as an iterative evidence-acquisition process over an explicit, mutable research state. A research question is broken into a tree of subquestions, each served by search intents that are translated into source-specific queries over arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar and the web. Results are merged into a canonical, provenance-preserving document registry through a conservative four-tier deduplication hierarchy. The registry is expanded by citation snowballing until a saturation criterion is met, and then screened, ranked and allocated to subquestions round-robin. Documents are read in parallel into a structured evidence store of claims with support, location, type and strength. A critic reviews the state along eight dimensions and returns research actions rather than a binary verdict: it can add, split, rephrase, deprioritize or close subquestions, so the research plan is an output of the investigation as well as an input. The final report is written section by section from the evidence store, and every citation resolves to a retrieved document. We describe the design, the deterministic machinery that keeps a language-model pipeline auditable, and a case study that read 28 of 237 retrieved documents in about three and a half minutes. We also report weaknesses the case study exposed.
Aaron J. Li, Weijia Xu, Chandan Singh et al. · cs.CL
Agents 93%
Abstract
Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, whereas real-world developers use them to continuously build, update, and maintain large-scale projects. This mismatch motivates us to evaluate agents over sequences of realistic coding tasks, where we find that agents exhibit recurring environment-dependent token costs that existing methods struggle to reduce. To minimize these costs, we introduce TokenEconomizer, an external controller that cuts environment-specific token costs over a sequence of tasks. These cuts come from determining (i) which operational micro-skills to inject, (ii) which persistently irrelevant tools to prune, and (iii) when to intervene in unproductive failure loops. Across Claude Code, Codex, and GitHub Copilot CLI paired with frontier models, TokenEconomizer reduces the average token cost by 18.4-30.9% with comparable task success. Savings hold in every repository under every tested agent-model setting and generalize to diverse domains such as sequential web development and security auditing, where costs fall by 6.4-21.2% depending on task structure. Our work establishes adaptive black-box cost control as a promising direction for reducing token costs of coding agents in realistic settings.
Ruida Wang, Gerald Friedland, Tong Zhang et al. · cs.LG
Agents 91%
Abstract
Enhancing the agentic capabilities of Large Language Models (LLMs) to tackle complex software engineering (SWE) and general terminal-usage problems is a pressing challenge. Current state-of-the-art LLMs often go through large-scale agentic Reinforcement Learning (RL). However, they mostly rely on high-level outcome rewards, with minimal consideration of low-level toolcall and mid-level workflow-stage rewards, which makes the training less effective. To overcome this limitation, we propose **Lean4AgenticRL**, which, to the best of our knowledge, is the first framework that grounds multi-level process rewards in the unified Lean4 formalization schema for open-ended agentic RL. **Lean4AgenticRL** first builds a *problem-specific workflow* system that balances the agent's own capability and controllability during execution, laying the foundation for further verification. Subsequently, our workflow formalization and multi-level reward annotation methods enable agent behavior verification within a general harness system. It provides multi-level rewards to support more effective agentic RL with the workflow-stage-normalized GRPO algorithm. Using **Lean4AgenticRL**, we train **LAR-9B/27B**, a family of models with enhanced agentic capability. Extensive experiments indicate that our model outperforms the leading model of similar size. **LAR-27B** achieves **77.3%** on TerminalBench-2.1. On average, our models outperform the base model by **9.89%** and surpass the second-best model of comparable size we know by **5.07%**. These results indicate the potential of integrating formal methods in enhancing open-ended agentic RL.
Bowen Ding, Qixin Wang, Lexing Ruan et al. · cs.AI
Multi-agent 91%Agents 72%Agent evaluation 70%
Abstract
LLM agents are increasingly integrated into real-world works, yet they must handle diverse domain-specific tools and complex multi-sub-task problems that sequential tool invocation resolves inefficiently and with severe context bloat. The Main-Agent Delegation and Sub-Agent Execution (MAD-SAE) paradigm addresses these issues by delegating sub-tasks to specialized sub-agents for parallel execution in isolated contexts, but its delegation and orchestration quality remains unquantified. We introduce MS-Eval, a unified evaluation kit comprising an MCP-intensive benchmark, a controlled execution harness, tailored delegation and orchestration metrics, and the MSQ index for comprehensive assessment. Evaluating four MAD-SAE variants and eight frontier models reveals that (1) sub-agent specialization (Spec) is the best practical practice; (2) open-source models are largely competitive with few exceptions; and (3) MAD-SAE generally raises cost with contingent payoff, benefiting most open-source models in both performance and efficiency while leaving closed-source models with higher cost and degraded performance. Our case study further traces these gains to better single-agent solutions, effective context offloading, and genuine sub-task parallelism, whereas unnecessary or redundant delegation turns the same cost into pure overhead. Codes: https://github.com/LINs-lab/MS-Eval
Real-world frontend development requires agents to compose reproduction, generation, modification, and repair over an evolving application state. Learning a general policy for this process requires translating heterogeneous execution feedback into task-aligned rewards and effective credit assignment across long sequences of interdependent actions. We introduce WebCoder, a general frontend development agent trained with artifact-grounded agentic reinforcement learning. Our key idea is to assess diverse development activities through their effects on a shared executable artifact and its satisfaction of task requirements. We build Webdev-World, an executable environment that integrates code editing, application execution, browser inspection, and on-demand skills while preserving project state across interactions. An independent verifier evaluates the final application against task requirements to provide terminal rewards, while changes in intermediate artifact progress redistribute the resulting rollout advantage across development segments. Context compaction and message-tree sample construction support training on trajectories beyond a single context window while avoiding repeated loss computation on shared generated history. We further introduce Webdev-Bench to evaluate composed development requirements within a single project. On Webdev-Bench, WebCoder-27B raises requirement satisfaction from 64.8 for its Qwen3.8-27B base model to 72.8, exceeding Claude-Opus-4.8 (65.1) and GPT-5.4 (59.6); on Vision2Web, it improves the average visual and functional score from 41.1 to 62.4, on par with Claude-Opus-4.8. Ablation studies confirm the contributions of artifact-grounded credit assignment and long-horizon training.
Jingting Zheng (TJUNLP Lab, School of Computer Science, Technology et al. · cs.CL
Multi-agent 91%
Abstract
Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining priors. We study Bai-Chinese translation in the Bowen script, where Chinese characters are frequently borrowed phonetically rather than semantically, causing severe literal-translation hallucinations. We propose MAS-Bai, a linguistically informed adaptive multi-agent framework for Bowen-script Bai-Chinese translation. MAS-Bai routes each input through either a lightweight retrieval-translation path or a deeper philological path with etymological and syntactic agents, and uses cycle-consistency with a lightweight reverse translator as an inference-time reliability signal. We construct a 6,536-sentence Bai-Chinese corpus and evaluate on a 1,536-sentence test set. MAS-Bai achieves 16.23 BLEU and 62.15 COMET, improving over Standard RAG by 8.11 BLEU and 6.85 COMET. Forward LoRA, expert ablations and controlled routing experiments distinguish the roles of supervised adaptation, Bai-specific expertise and conditional routing. The largest gains occur on Bowen phonetic loans and divergent Bai word order, while human evaluation and reverse-verifier analyses support the automatic results.
We present FRACTAL, a self-similar multi-agent architecture for recursive goal decomposition, in which the same five-component organizational pattern -- Orchestrator, Ensemble, Knowledge Ledger, Decision Maker, Meta-Observer -- recurs at every level of a decomposition tree. We make four formal contributions: (1) a communication bound showing intra-node cost is linear in ensemble size and round count (O(kr)) under a two-phase blind-proposal/stress-test protocol, versus quadratic cost for free-form debate, with an explicit, stated assumption on fixed evaluator count; (2) a two-mode orchestration criterion separating generative and evaluative phases via a measurable diversity-saturation threshold; (3) a supermajority convergence guarantee with explicit probability bounds at stated agreement levels, and a formal depth bound under an operationalized goal-complexity measure; (4) a Bayesian inter-layer escalation mechanism unifying hysteresis and contract-breach signaling under one posterior update. We illustrate the architecture's execution qualitatively on a worked example and a multi-layer case study; we do not report quantitative performance claims in this paper, and we explicitly discuss the formal and inductive-bias limitations of the model, including an unimplemented but architecture-compatible direction toward bounded self-improvement. We use "fractal" as an architectural metaphor for self-similarity, not a measured mathematical property. Empirical validation of the architecture's comparative performance is left to future work.
Text detoxification requires balancing toxicity removal, semantic preservation, and fluency. Existing methods typically optimize an unconstrained scalar objective---enabling safety scores to mask semantic loss---or rely on open-ended iterative debate prone to semantic drift and high computational cost. We propose AMEND, an inference-time framework that decouples detoxification into role-conditioned proposal generation, isolated multidimensional criticism, and constraint-first selection. AMEND evaluates diverse candidates with role-blind critics and enforces strict semantic and fluency feasibility before ranking by utility. To maximize efficiency, AMEND Lite restricts subsequent search to at most one targeted repair round only when residual toxic spans remain. On ParaDetox, one-round selection over diverse roles improves the joint evaluation metric by $+0.0508$ over the best single role. On a frozen confirmation test set, AMEND Lite achieves a joint score of $0.6597 \pm 0.0062$, outperforming unconstrained multi-round loops by $+0.0489$ ($p < 0.05$) while reducing inference requests by 28.4%.
Yuxing Chen, Zhisheng Zhang, Cheng Tang et al. · cs.AI
Agents 90%Multi-agent 39%
Abstract
Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable agent harness coupling composable scientific execution with conditional skill induction. Its environment integrates over 80 scientific operations, biomedical resources and task-specific code, preserving associations among candidates, results and artifacts. From execution trajectories and outcome feedback, DrugHarness induces action hypotheses with observable applicability conditions, recommended actions and supporting evidence. An independent review agent evaluates candidate skills derived from these hypotheses through source verification and, when needed, targeted execution trials. Admitted skills guide subsequent tasks and are revised through feedback. Evaluation on MolBench and SMDD-Bench demonstrates capabilities in molecular screening, optimization and constrained design. Without evolution, DrugHarness exceeds reported MolClaw-CC results by 10.8 percentage points in affinity-comparison accuracy and 55% in mean top-three active hits on MolBench. Retrospective evaluation on skill-development tasks shows that evolution increases Qwen's affinity-comparison accuracy from 62.2% to 81.1% and optimization success from 79.5% to 87.2%. In a prospective HPK1 study, DrugHarness achieves a more favorable median docking score than Biomni among system-specific candidates. A synthesized compound achieves a cellular IC50 of 14.19 nM, a 2.64-fold potency improvement over the best input reference, with activity competitive with two selected compounds designed by experienced medicinal chemists. These results support conditional skill evolution for scientific agents and demonstrate a workflow connecting computational drug design with experimental validation.