All Articles · SURL AI News

GitHub Agentic autofix integrates with Copilot Memory, enabling security fix patterns to be reused across tasks

When handling security alerts, the agent can consult existing memories and save newly generated fix patterns for other Copilot features to use. The feature remains in public preview, and GitHub has not published data on improvements to success rates or costs.

2026-09-26

AI 研究

AgenticGenPlan Generates Robot Planning Programs Without LLM Calls During Evaluation

The study tests reusable control programs in 28 simulated environment types. In the subset with classical planner comparisons, the best method reaches a 95% average success rate. Results are limited to fully observable states; reproducing them requires checking black-box access controls, evaluation seeds, and upfront synthesis costs.

2026-09-26

Sarvam Vision 2.1 Adds Structured Form Extraction and Handwriting Recognition for Indian Languages

The new version combines layout parsing with a vision-language model to support cross-page tables and form-field extraction. The official evaluation changed some of its test coverage, and API model-version mappings should be checked before deployment.

2026-09-25

AI 研究

RECLAIM tests research agents on 100 papers; full-materials group reaches a 41% reproduction rate

The benchmark asks agents to install dependencies, debug issues, and run experiments themselves, then has an independent model audit the execution evidence. Public code and traces let developers trace points of failure, but the results remain limited by model coverage and single-run testing.

2026-09-25

GitHub Repo

langchain-anthropic 1.7.4 Supports Adding and Removing Tools Mid-Conversation

The new version uses system messages to convey tool changes, allowing agents to adjust their capabilities in stages and potentially preserve existing prompt caches. The feature is still subject to model, message-position, and cache-setting limitations, and no performance test data is available.

2026-09-25

GitHub Repo

langchain-fireworks 1.6.3 Wraps Invalid Historical Arguments to Fix Agent Conversation Resumption

The new release wraps malformed or non-object JSON from historical tool calls in diagnostic data, preventing a subsequent request from being rejected because of stale arguments. The change preserves call-and-result pairing; actual task recovery rates remain unverified.

2026-09-25

AI 研究

JitMem tailors agent memory to new tasks, raising success rates by over 16 percentage points on two benchmarks

The research preserves raw trajectories from successful tasks and generates relevant summaries only when the next task arrives. The gains come from specific benchmarks and model configurations, and deployment assessments must still account for the memory curation model’s additional costs.

2026-09-25

GitHub Repo

TensorFlow 2.22 Release Candidate Adds Tiered Batch Waiting and a Separate Warmup Thread Pool

BatchFunction adds configurable wait times by request criticality and a control for handling warmup work in a separate thread pool. No performance benchmarks have been published; deployments still need to validate scheduler settings and tail latency.

2026-09-25

GitHub Repo

Hermes Agent 0.21.5 Adds Per-Profile Start and Stop Controls for Partial Shared-Gateway Maintenance

The release lets admins independently stop and start a selected agent on a shared gateway, with a persistent marker to retain its disabled state. Already-dispatched scheduled jobs continue running, and compatibility should be checked for older multi-process deployments.

2026-09-25

GitHub Repo

Ultralytics 8.4.162 adds image batch prefetching to overlap loading with CUDA inference

The new release uses a background thread to preload the next batch of images, reducing the time the GPU spends waiting for data. Published benchmarks cover specific YOLO26n configurations, while the release summary and merge history still differ on the feature’s scope.

2026-09-25

AI 研究

Xiaomi unveils HySparse2, reducing million-token prefill compute to about one-fifth of the baseline

The architecture uses two levels of KV sharing to end prefill early for long inputs. The fivefold difference comes from computational analysis; quality evaluations extend to 256k, while real-world serving latency remains unverified.

2026-09-25

GitHub Repo

AutoGPT 0.8.1 Centralizes Sandbox Connections, Adds Optional TCP Egress Proxy

The release centralizes E2B sandbox creation, reconnection, and proxy credential rotation. The feature is disabled by default and requires an external proxy; DNS and QUIC traffic fall outside this TCP channel.

2026-09-25