代理工具

Agent、MCP、coding agent、工作流自動化與評測。

PDDLCoder Lets Agents Iteratively Fix PDDL, Achieving an 89.6% Executable Success Rate on 106 Unseen Planning Problems

Rather than requiring a language model to directly generate long-horizon action sequences, PDDLCoder first constructs a PDDL world model that can be verified by a symbolic planner. DeepSeek V4 Flash solved 95 of 106 problems across four held-out domains, but results for different base models ranged from 89.6% to zero, showing that the framework’s effectiveness depends heavily on a model’s ability to follow formatting requirements and use tool feedback.

2026-08-18

推論系統

FluxBin Uses Binary Bases with a LUT CUDA Kernel, Reports Up to 5.92× Faster Inference on a Single A100

Rather than expanding ultra-low-bit weights back into FP16, FluxBin uses binary patterns to directly index precomputed partial sums. The paper reports up to a 5.92× speedup and a 10.19× improvement in energy efficiency on a single A100, but its public code link remains inaccessible.

2026-08-18

代理工具

Kozuchi Takes the Same 27B Code-Repair Agent to Java, Solving 41 of 128 Multi-SWE-bench Tasks

Fujitsu ported its fine-tuning-free Qwen3.5-27B setup, eight-stage repair workflow, and cross-agent test selector to Java unchanged. It solved 374 of 500 tasks on the Python SWE-bench Verified benchmark, but achieved only a 32.03% success rate on Java, showing that agent-framework portability does not imply equal language proficiency.

2026-08-18

PertMind Trains a 4B Model on Cellular Perturbation Endpoints, Turning 100 Million Single-Cell Profiles into Reinforcement Learning Rewards

Starting from Qwen3-4B, PertMind combines gene responses, pathway direction, and output formatting into computable rewards, eliminating the need to manually author large numbers of biological reasoning traces. The model transfers zero-shot to inverse perturbation identification and dual-perturbation tasks, but its natural-language mechanistic explanations still cannot be treated as causal proof.

2026-08-18

推論系統

R³-Bench Gives Six Problems a Shared Reasoning Budget; Models Fall Below Their Own Offline Upper Bound in 71 of 72 Test Settings

The new evaluation no longer provides a separate allowance for each problem. Instead, models must allocate tokens or tool calls across six problems. Even though all six models can solve the problems individually, under a shared budget they generally fail to direct compute toward the problems with the highest expected payoff.

2026-08-18

代理工具

RelArena-α Uniformly Reruns 21 Relational Data Tasks, With TabPFN-Rel Leading Among Models Using Standardized Tuning

Prior Labs has open-sourced a unified workflow for data splitting, hyperparameter tuning, and evaluation, enabling a fresh comparison of graph models, relational Transformers, and tabular methods. TabPFN-Rel shows that aggregating relational data before passing it to a tabular foundation model remains competitive, although the CPU cost of feature synthesis is not fully included in the leaderboard’s timing results.

2026-08-18

推論系統

FreeToken Dynamically Splits MoE Cache Misses, Runs a 35B Model at 39.3 token/s on an 8GB RTX 4060

Based on host memory and PCIe bandwidth, FreeToken dynamically decides whether experts missing from the cache should be transferred to the GPU or computed directly on the CPU. The paper reports 1.3× to 2.1× higher decoding throughput than the strongest baseline across five consumer-grade systems, but the linked code repository is not currently publicly accessible.

2026-08-18

代理工具

Success Rates Hold After Agent Context Compression, but GPT-5.5 State Rechecks Still Triple

A new evaluation separates tool calls into state retrieval and task execution, finding that context compression can sharply increase an agent’s rechecking costs before success rates decline. Under fivefold compression, GPT-5.5’s completion rate changed from 80% to 85%, while its average retrieval calls rose from 21.0 to 63.9.

2026-08-18

推論系統

DriveCache Allocates Denoising Cache Based on Planned Vehicle Trajectories, Maintaining Higher Fidelity at 1.97× Speed on Wan2.2 A14B

DriveCache uses vehicle translation and rotation known before generation to schedule diffusion-model feature reuse across different driving scenarios. On Wan2.2 A14B, it delivers 1.276 dB higher PSNR than SeaCache at a nearly identical acceleration level, though the code has not yet been released.

2026-08-18

代理工具

Multi-Agent Programming Teams Replace Point-to-Point Messages With Shared Files, Cutting Output Tokens by About 42% With Eight Agents

UCL researchers modeled agents, files, messages, and read/write events as a temporal network and analyzed 1,902 controlled programming tasks. The results show that collaboration topology is determined mainly by task structure; merely designating a coordinator in the prompt did not create an actual hub.

2026-08-18

代理工具

After an Agent Completes an Audit and Repair, Its False-Positive Rate in the Next Verification Falls by Up to 11.5 Percentage Points

New research shows that even when the content being verified is identical, prior auditing and repair experience retained in context causes several open models to flag fewer errors. Signal detection analysis found no corresponding improvement in discriminability, suggesting that the agent pipeline changes the verification threshold rather than simply making the model more accurate.

2026-08-18

代理工具

Quipu Changes Agent Writes to Knowledge Graphs from Accept-Then-Clean to Validate-Before-Commit, with Rejected Records Replayable Across Versions

Quipu places data, trust labels, rules, and decisions on dual timelines, and checks candidate state before committing agent writes. In the authors’ injected-defect test, all six defects persisted without a gate, compared with zero under Quipu, though the evidence still comes mainly from a single deterministic evaluation designed by the system’s authors.

2026-08-18