代理工具

Agent、MCP、coding agent、工作流自動化與評測。

Restricting Module Visibility Fosters Reusable Latent Communication; Restricted Models Lead by at Least 20 Points in 9 of 10 Paired Experiments

Four modules sharing Qwen2.5-0.5B and the same LoRA learned radically different composition strategies solely because of different attention masks. Limiting each module to its own evidence fragment made it easier to develop intermediate-value communication that transferred across examples, but the experiment still missed its preregistered overall success threshold by 0.0012.

2026-08-21

MidTool Moves Tool Use into Mid-Training, Raising Qwen3-4B’s BFCLv3 Overall Score by 10.5 Points

MidTool-Mix synthesizes 20.3 billion tokens from web pages, PDFs, code, and real-world tool interfaces, enabling models to learn tool boundaries, parameters, and workflows before SFT and RL. With the same SFT recipe, Qwen3-4B’s BFCLv3 overall score rises from 39.73% to 50.25%, although deep-search tasks remain entirely unsolved.

2026-08-21

AI 安全

Even a Frozen Qwen3-8B Shows “Capability Expansion,” Prompting Researchers to Call for Empirical Null Baselines in Self-Improvement Evaluations

New research finds that single-run greedy decoding and unstable thresholds can make a completely untrained model appear to gain or lose capabilities. After switching to exact per-item tests, three forms of self-training only consistently strengthened existing capabilities, with no evidence that they acquired new capabilities never demonstrated by the base model.

2026-08-21

代理工具

PILOT Manages Taobao Recommendation Experiments with Deterministic Guardrails, Raising Search Efficiency from 53.3% to 93.3%

PILOT assigns experiment management, segment-specific strategy search, and memory curation to three LLM roles, while reserving permissions, statistical decisions, and state writes for deterministic services. Internal results from five online Taobao buckets show a 40-percentage-point increase in search efficiency, but the report provides neither publicly reproducible code nor traffic volumes.

2026-08-21

代理工具

CentaurBench: The Model Best at Solving Problems Independently May Not Be the Best at Guiding Another Agent

CentaurBench separately evaluates models’ automation and assistance capabilities across seven work tasks, finding a correlation of only about 0.48 between the two rankings. Unassisted GPT-3.5-Turbo outperformed every guided version on three tasks, showing that adding a powerful model does not necessarily improve an agent workflow.

2026-08-21

代理工具

TrueForge Open-Sources Agent Execution Framework, Claims 30% to 75% Lower Costs Across 14 Enterprise Tasks

TrueFoundry has released TrueForge under the MIT License, combining agent loops, MCP tools, on-demand sandboxes, subagents, and approval workflows into a self-hostable execution framework. In its Enterprise-Bench report, the company claims savings of about 30% using the same model and about 75% after switching to GLM-5.2, although the comparison covers only 14 tasks.

2026-08-21

代理工具

Slack Code Brings Coding Agents into Shared Channels, With Diff Views, Live Previews, and Human Approval

Salesforce has launched Slack Code, allowing teams to create project-specific Code Channels directly from conversations and collaboratively monitor, revise, and approve agent-generated code. Initial integrations include Claude, Devin, GitHub Copilot, ChatGPT, and Vercel agents, but details about security isolation, permission granularity, and APIs have yet to be fully disclosed.

2026-08-21

代理工具

AFANet Diagnoses Multi-Agent Failures With 65K Trainable Parameters, Cutting In-Domain Inference From 199 Seconds to 1.16 Seconds

AFANet converts agent conversations into graphs with temporal and same-agent edges, then uses a two-layer GCN to identify faulty agents and error types. It outperforms several LLM baselines on AEGIS-Bench, but its agent–error pair F1 remains low across datasets.

2026-08-20

代理工具

DeepWeaver Weaves Evidence Before Generating Answers, Raising DeepSeek-V4-Flash’s Argument Sufficiency from 75.4% to 86.5%

DeepWeaver uses a Thought Block Chain to organize claims, key information, and sources, then repeatedly checks for evidence that has not yet been used. It improves long-form responses and citation metrics across several models, but the new benchmark focuses on Chinese-language water environment questions, and the code has yet to be released.

2026-08-20

推論系統

Liquid AI Adds DSpark Draft Models to LFM2.5, Delivering Up to 3.18× Faster Decoding on a Single H100

Liquid AI has released three DSpark draft models with roughly 300 million parameters, enabling LFM2.5 to verify multiple candidate tokens at once through speculative decoding. Tests with batch size 1 and greedy decoding showed speedups of up to 3.18×, but SGLang support remains in an open PR, leaving deployment maturity yet to be validated.

2026-08-20

代理工具

SkillForge Synthesizes Failures from Project Tests First, Lifting SWE-bench Verified Scores by More Than 5 Points for Two Coding Agents

Before real-world issues arrive, SkillForge creates verifiable failures from execution paths covered by tests, then distills repair trajectories into project-specific skills. When paired with Mini-SWE-Agent, it raises SWE-bench Verified Pass@1 for DeepSeek-V3.2 and GPT-5-mini to 72.2% and 60.6%, respectively.

2026-08-20

代理工具

SPADE Has the Same LLM Write Executable Training Environments, Improving a 30B Model by an Average of 5.3 Points Across Eight Benchmarks

SPADE trains the environment designer using the return gap between runs with and without hints, allowing the curriculum to become harder automatically as the agent improves. Qwen3-30B-A3B gained as much as 13.9 points on tool-use benchmarks, though environment validators may still accept underspecified or unsolvable tasks.

2026-08-20