TL;DR Advanced encoders were losing to older models on sparse retrieval for one surprising reason: a vocabulary mismatch. Fixing it with just 20k adaptation steps sets a new BEIR state of the art. Title: Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps URL: Key points 🔤 Raw case-sensitive vocabularies were splitting single meanings across redundant surface forms 🧩 The proposed Vocabulary Transfer method migrates vocabularies in 3 lightweight steps 📊 ModernBERT-VT hits nDCG@10 52.4 on BEIR, a new SOTA 💥 A collapsed RoBERTa-large jumps from BEIR score 1.4 to 51.3 ⚡ Uses under 0.2% of the original pretraining token budget 🧪 Near-optimal performance reached in just 500 MLM steps 🧬 Also works for domain-specific vocabularies like chemistry It's a nice reminder that what looked like an architectural ceiling turned out to be a fixable vocabulary design problem. #InformationRetrieval# #LLM#

🔄 TL;DR: A search index that diagnoses its own weaknesses, rewrites its keys, and validates the changes — all without any human in the loop. It beats existing methods by a wide margin on BRIGHT. Title: Self-Evolving Search Index URL: Points 🩺 Builds co-retrieval profiles from search results to self-diagnose whether documents are well distinguished, with no human annotation needed ✍️ Selectively revises key sets only for flagged documents, autonomously deciding up to 10 keys per document ✅ Self-validates proposals on faithfulness, specificity, and separation, keeping only keys that pass 🔍 A Query Simulator proactively probes uncovered demand with synthetic queries 📈 Hits 22.8 average nDCG@10 on BRIGHT, +9.2% over RL-Index and +40-57% over the base index 🤖 For search agents, answer accuracy jumps +77.87% while search calls drop -16.80% The idea of making index optimization itself self-evolving, not just the model or the agent, is what makes this interesting. #InformationRetrieval# #LLMAgents#

3 ways I'm using Grok Bot plugins Information retrieval: First, you can ask questions and pull context from multiple workspaces, slacks, and google accounts - Grok @Bot supports multiple accounts per connection. This is helpful when information is scattered or you find yourself switching between multiple apps. Grok Bot has saved me hours as a simple search tool. "I think I saw an invite for an event on Friday, but I can't remember if it was in Slack or Gmail - can you find it for me?" Bi-directional sync: Because Grok Bot has triggers & routines - you can make a zero-code bi-directional sync: "Make sure events on my personal calendar are always blocked on my work calendar" Or get more advanced: "Every Monday, take my tasks in Todoist and Google Calendar and block time on my work calendar for deep work, hold time for personal events (going to the gym, etc), and ensure each task has some time scheduled" Sync across channels: I use Grok Bot to make sure I capture feedback across channels and sync deliverables. Because Grok Bot can kick off cloud agents, this is perfect for flows with tons of context switching. "There's a launch happening this Friday, I have a draft for the changelog on GitHub, but the team is leaving feedback in Notion and Slack. The header asset is in Figma. Keep an eye on the feedback and consolidate it for me here. Then, kick off a Cursor cloud agent to update the PR and make adjustments in Figma as necessary" This has drastically reduced context switching typically associated with knowledge work and allowed me to focus more on what matters - being creative. I found plugins to be one of the biggest differentiators from other personal agents. Shout out to the team for the rock-solid experience.

# Decision Points for Embedding AI Agents in Enterprise Systems # Autonomous vs Deterministic Workflow 🎯 The Hook Are you letting your agent "figure it out" or telling it "follow these exact steps"? Autonomous is flexible but unpredictable. Deterministic is rigid but auditable. If you choose "autonomous by default" without evaluating the reversibility and impact of side effects, you risk handing irreversible operations to an agent's free-form judgment — and that is a recipe for unrecoverable damage 🔑 📋 Overview The autonomous approach lets the agent freely plan and execute steps. It excels when task variations are too numerous to predefine all flows, and the operations are primarily read-only — information retrieval, summarization, analysis — where mistakes are easily reversible. The deterministic workflow approach forces the agent to follow predefined flows. It is the right choice when operations have irreversible or high-impact side effects (payment processing, contract modification, production deployment, HR changes) and when SOX, GDPR, or financial regulations mandate audit trails 📊 🔍 Decision Points The decision is driven by the presence and reversibility of side effects: No side effects (read-only) → Autonomous is fine Side effects + reversible → Autonomous with post-verification works Side effects + irreversible → Deterministic with pre-approval is mandatory Regulatory requirements → Deterministic with audit trail Task diversity is also a factor. Fixed patterns benefit from deterministic optimization. Diverse, unpredictable tasks need the flexibility of autonomous mode. Even in autonomous mode, inserting HITL (Human-in-the-Loop) approval gates before high-risk operations preserves safety ⚡ 💡 Key Details Production systems rarely use pure autonomous or pure deterministic — hybrid is the norm: Autonomous planning, deterministic execution: The agent autonomously decomposes and plans the task, but each step follows a predefined workflow (API call ordering, validation, approval gates). This pattern balances planning flexibility with execution safety. Risk-level routing: Read operations route to autonomous mode, write operations route to deterministic workflows. Combining this with dual-track verification is the standard approach. Consider ServiceNow incident response: root cause investigation runs in autonomous mode (flexible log searching, hypothesis generation, verification), while recovery operations follow deterministic mode (predefined runbook procedures). Record audit trails across all modes. Even in autonomous mode, operation logs that explain "why this action was taken" are essential 🔄 ⚖️ Trade-offs Delegating irreversible operations to autonomous mode carries enormous risk. An agent autonomously deciding to bulk-update prices on thousands of Shopify products can cause real financial damage when it gets the pricing wrong 😩 On the other side, making everything deterministic locks down information retrieval and summarization into rigid flows, killing the agent's flexibility entirely. At that point, it is no different from a traditional rule engine — the "AI agent" label becomes meaningless. Ambiguous hybrid boundaries are equally dangerous. When the switching conditions between autonomous and deterministic are not codified, implementations vary by developer. Define risk classifications for operations first, then codify the switching logic ⚠️ 🛠️ Use Cases Knowledge search + document editing: Searching and summarizing knowledge in Notion/Confluence runs in autonomous mode (read-only, flexible exploration creates value). Publishing documents or changing sharing permissions uses deterministic workflows (approval gate + audit log) 📚 E-commerce operations (Shopify): Product search and analysis is autonomous. Inventory adjustment is deterministic (change magnitude validation + approval). Bulk price changes are deterministic with mandatory dry-run (diff preview → human confirmation → execution). The same agent switches execution models based on risk level 🛒 Incident response (ServiceNow): The investigation phase is autonomous (log search → hypothesis → verification, flexibly). The recovery phase is deterministic (follow runbook procedures, with approval gates at each step). Investigate freely, execute strictly 🔧 Practical tip: Define the boundary between autonomous and deterministic as a risk classification table before writing any code. Categorize each operation as "read," "reversible write," "irreversible write," or "financial transaction," and assign the execution model for each. This is the starting point for safe agent operations 💪 #AIAgents# #EnterpriseArchitecture#

Financial work depends on trustworthy sources, consistent definitions, accurate calculations and auditable outputs. Introducing Ling-3.0-flash-Fin, a finance-enhanced version of Ling-3.0-flash, developed with financial institutions and domain experts. With 124B total and 5.1B active parameters, it supports information retrieval, research, valuation modeling and report preparation across long reports, research materials and complex workbooks. The model showed competitive results across FinFIRST, FinSearchComp Verified, FinCRAFT, FinanceAgent v1.1/v2, APEX-Agents, SpreadsheetBench v1/v2 and τ³-Banking. We will open-source the model weights next week.

# Decision Points in AI Agent Development # Single Agent vs Multi-Agent 🤖 🎯 The Hook Multi-agent systems look impressive. But "impressive" is not an architecture rationale. The real question: does the benefit of separating specializations outweigh the coordination cost? There is no "just a little multi-agent." The boundary between single and multi is discontinuous -- you either introduce coordination infrastructure or you don't. 📋 Overview A single agent is one LLM instance holding all tools, all context, and all permissions, processing the entire task. Control flow completes within a single loop with no inter-agent communication. A multi-agent system has multiple specialized Workers coordinated by a Supervisor. Each Worker holds only the tools and context for its domain. The Supervisor handles task decomposition, budget allocation, and result aggregation. 🔍 Decision Points Two axes drive this choice. 1️⃣ **Task variability and specialization separation** - Tool set fits within 20 tools and one context window → Single - Specialization axes split into 2+ distinct domains where mixing creates noise → Multi - Parallel execution of independent subtasks helps meet latency budgets → Multi 2️⃣ **Cost sensitivity** - Cannot tolerate increased LLM call volume → Single - Coordination overhead (Supervisor token consumption, error propagation design) is less than the benefit of separation → Multi 💡 Key Details 🟢 **Single agent excels in simplicity and cost efficiency.** Debugging stays within one context window. Testing validates one agent's inputs and outputs. No state-sharing problems, no consensus needed. As long as everything fits in the context window, all information is available to a single inference with zero information transfer loss. In a multi-agent setup, Supervisor task decomposition + independent Worker LLM calls + result aggregation can inflate token consumption by 3-5x. 🟡 **Multi-agent excels in three areas: specialization isolation, minimal permissions, and parallel execution.** Each Worker's context window contains only domain-specific information, improving inference accuracy. Permissions are granted per Worker under least-privilege principles -- if one Worker is compromised, damage is contained. Independent subtasks can run in parallel to save latency. ⚖️ Trade-offs | Dimension | Single Agent | Multi-Agent | |---|---|---| | Debugging | Contained in one context 🟢 | Distributed tracing required 🔴 | | Cost | One LLM loop | 3-5x token consumption | | Inference accuracy | Degrades beyond ~20 tools | Improves with specialization | | Security | All permissions concentrated | Per-Worker permission isolation | | Parallelism | Not possible | Available for independent subtasks | 🛠️ Use Cases 🔵 **Single agent fits**: Information retrieval, summarization, classification with a limited tool set. Cost-sensitive projects. Tasks where specialization has only one axis. 🔴 **Multi-agent fits**: Code generation + test execution + review, where specialization axes are clearly distinct. Tasks requiring different domain expertise (legal + technical). Systems where security demands permission isolation. 📌 **Default strategy**: Start with a single agent. Coordination costs in multi-agent systems are consistently underestimated. When bottlenecks become clear -- context overflow, coarse permissions, latency limits -- add the minimum Workers needed to resolve them. Keep Worker count at 2-5; beyond that, evaluate coordination cost growth carefully. #AIAgents# #SoftwareArchitecture#