v2.1.183 improves auto mode safety by blocking destructive git and destroy commands without explicit user consent. It adds deprecation warnings for models, introduces attribution.sessionUrl to hide session links, and fixes multiple issues including terminal behavior, subagent performance, and input handling in web and tmux environments.
The autogpt-platform-beta-v0.6.64 release, dated 18th June 2026, introduces new features such as the AutoPilot Context Panel and Global Search, along with enhancements to graph saving, caching, and builder performance. It also includes security hardening, bug fixes for LLM provider issues, and UI improvements like a high-resolution touch icon.
Claude Code v2.1.181 introduces support for setting config settings via prompt syntax like /config thinking=false, adds sandbox Apple Events support on macOS, and improves streaming, auto-retry, and subagent behavior. It also fixes numerous bugs related to startup, file handling, clipboard, and UI responsiveness across platforms.
Claude v2.1.178 introduces new permission rules using Tool(param:value) syntax, improved workflow and skill loading in nested directories, and enhanced auto mode and error messaging. It fixes critical issues including crashes, authentication errors, and UI behavior in Chrome and VSCode, while refining tool prompts and undo functionality.
Anthropic launched Claude Fable 5, a Mythos-class model claiming state-of-the-art performance across software engineering, scientific research, and knowledge work. It was quickly taken down by the U.S. government after a jailbreak was reported, though Anthropic asserts it is now available again, with Fable 5 showing exceptional capabilities and a more nuanced, thoughtful reasoning style compared to prior models.
llama.cpp version b9718 consolidates slot selection into a single function, get_available_slot, while maintaining LCP similarity checks for prompt cache updates. The release includes binary builds for macOS, Linux, Android, Windows, and openEuler across multiple architectures and hardware acceleration options.
llama.cpp has released version b9721, offering binaries for macOS, Linux, Android, Windows, and openEuler across various architectures. The release includes CPU, Vulkan, ROCm, OpenVINO, SYCL, and HIP support, with a dedicated UI package. A feature for Apple Silicon with KleidiAI is currently disabled.
The v0.17.6 release adds pre-approval tool input guardrails and SDK-only custom data for tool outputs. It also enforces a strict JSON-compatible contract for tool outputs and suppresses unnecessary whitespace warnings in tool names. @siddiksawani made their first contribution in this release.
LLaMA.cpp version b9715 introduces CUDA support for GGML_OP_COL2IM_1D, building on a CPU implementation. The release includes binaries for macOS, Linux, Android, Windows, and openEuler across multiple architectures and acceleration frameworks, including Vulkan, ROCm, OpenVINO, and SYCL.
NRT-Bench introduces a benchmark for multi-turn red-teaming of LLM agents operating in a simulated nuclear power plant. Across four frontier operator models, 8.7% to 12.1% of attack sessions result in loss of a critical safety function, with vulnerabilities largely disjoint across models. The effectiveness of defences varies significantly by model, showing strong model dependence.
Agentic AI systems face growing threats from model-guided automated attacks. A new defense strategy, Contextual Misdirection via Progressive Engagement (CMPE), reduces attacker success rates by up to two orders of magnitude and nearly eliminates verified attack success in benchmark tests.
UltraQuant enables 4-bit KV caching for context-heavy agents, reducing P50 time-to-first-token by 3.47x in late rounds and boosting output throughput by 1.63x over FP8 KV baseline. It achieves this using FP8 queries, FP4 KV tensors, UE8M0 group scales, and native scaled-MFMA on AMD CDNA4 GPUs, with optimizations for decode-attention kernels and robust design choices like asymmetric K/V treatment and Walsh-Hadamard rotation.
Contagion Networks introduces a framework to measure how evaluator biases spread among LLM agents. In a 3-agent experiment, biases propagated consistently with contagion coefficients between 0.157 and 0.352, and homogeneous-model agents showed significantly weaker contagion than cross-model setups. Increasing evaluator committee size from k=1 to k=3 reduced effective contagion by 72.4%.
CWE-Trace evaluates eight vanilla and 15 LoRA-fine-tuned LLMs on Linux kernel vulnerability detection. Results show data contamination offers no advantage, and fine-tuning only shifts output thresholds without altering decision policies. Despite improved detection scores, LLMs lack reliable security reasoning, with top-1 CWE accuracy below 1.3% and binary detection performance at 52.1%.
A new framework enables secure, probabilistic policy enforcement for AI agents in ambiguous environments. It uses distributionally robust optimization to compute rigorous upper bounds on policy violation probabilities without assuming predicate independence. The method outperforms prior approaches on terminal and tool calling agent benchmarks, improving the security-utility trade-off.
LedgerAgent introduces a structured ledger to maintain task states separately in tool-calling agents. It renders states into prompts and enforces policy constraints before tool execution, reducing policy violations and improving performance across customer-service domains.
v1.14.8a2 adds a single agent action to Flow definitions and validates CEL expressions at load time. It includes a new Datadog integration guide with an importable operations dashboard and updated snapshot and changelog for v1.14.8a1.
UltraQuant introduces a 4-bit KV caching method tailored for context-heavy agent workloads. It achieves 3.47x reduction in P50 time-to-first-token in late rounds and 1.63x higher output throughput compared to FP8 KV caching, using FP8 queries, FP4 KV tensors, and native AMD CDNA4 scaled-MFMA support.
This paper introduces Marginal Advantage Accumulation (MAA), a post-processing architecture that addresses cross-batch inconsistency in memory-driven agent self-evolution. MAA formalizes alignment and comparability as structural conditions, uses differential signals and exponential moving average to accumulate signed evidence per operation, and ensures traceability via semantic identity merging. It outperforms batch-level baselines in 14 out of 16 settings and reduces token consumption by about 75%.
A new dataset, IFLLM, collects mouse trajectories and eye gazing data from users interacting with LLMs. It shows that implicit feedback significantly improves LLM alignment, boosting text-based reward model accuracy from 55% to 64% and nearly tripling response quality improvements after DPO training on eight LLMs.